Paper Digest: ECCV 2018 Highlights

September 9, 2018October 6, 2019 admin

The European Conference on Computer Vision (ECCV) is one of the top computer vision conferences in the world. In 2018, it is to be held in Munich, Germany. There were 2,439 paper submissions, of which 776 were accepted (59 orals, 717 posters).

To help AI community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights / summaries to quickly get the main idea of each paper.

We thank all authors for writing these interesting papers, and readers for reading our digests. If you do not want to miss any interesting AI paper, you are welcome to sign up our free paper digest service to get new paper updates customized to your own interests on a daily basis.

Paper Digest Team
team@paperdigest.org

TABLE 1: ECCV 2018 Papers

	Title	Authors	Highlight
1	Semi-convolutional Operators for Instance Segmentation	David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi	In this paper we show theoretically and empirically that constructing dense pixel embeddings that can separate object instances cannot be easily achieved using convolutional operators.
2	Learnable PINs: Cross-Modal Embeddings for Person Identity	Arsha Nagrani, Samuel Albanie, Andrew Zisserman	We propose and investigate an identity sensitive joint embedding of face and voice.
3	Learning-based Video Motion Magnification	Tae-Hyun Oh, Ronnachai Jaroensri, Changil Kim, Mohamed Elgharib, Fr’edo Durand, William T. Freeman, Wojciech Matusik	In this paper, we seek to learn the filters directly from examples using deep convolutional neural networks.
4	Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation	Xiaoxiao Li, Chen Change Loy	In this study, we formulate a deep recurrent network that is capable of segmenting and tracking objects in video simultaneously by their temporal continuity, yet able to re-identify them when they re-appear after a prolonged occlusion.
5	CBAM: Convolutional Block Attention Module	Sanghyun Woo , Jongchan Park , Joon-Young Lee, In So Kweon	We propose Convolutional Block Attention Module (CBAM), a simple and effective attention module that can be integrated with any feed-forward convolutional neural networks.
6	BodyNet: Volumetric Inference of 3D Human Body Shapes	Gul Varol, Duygu Ceylan, Bryan Russell, Jimei Yang, Ersin Yumer, Ivan Laptev, Cordelia Schmid	In this work we argue for an alternative representation and propose BodyNet, a neural network for direct inference of volumetric body shape from a single image.
7	CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfaces	Satoshi Ikehata	This paper presents a photometric stereo network that directly learns relationships between the photometric stereo input and surface normals of a scene. For training the network, we create a synthetic photometric stereo dataset that is generated by a physics-based renderer, therefore the global light transport is considered.
8	Spatio-temporal Transformer Network for Video Restoration	Tae Hyun Kim, Mehdi S. M. Sajjadi, Michael Hirsch, Bernhard Scholkopf	To alleviate these problems, we propose a novel Spatio-temporal Transformer Network (STTN) which handles multiple frames at once and thereby manages to mitigate the common nuisance of occlusions in optical flow estimation.
9	PS-FCN: A Flexible Learning Framework for Photometric Stereo	Guanying Chen, Kai Han, Kwan-Yee K. Wong	In this paper, we propose a deep fully convolutional network, called PS-FCN, that takes an arbitrary number of images of a static object captured under different light directions with a fixed camera as input, and predicts a normal map of the object in a fast feed-forward pass.
10	Dynamic Conditional Networks for Few-Shot Learning	Fang Zhao, Jian Zhao, Shuicheng Yan, Jiashi Feng	This paper proposes a novel Dynamic Conditional Convolutional Network (DCCN) to handle conditional few-shot learning, i.e, only a few training samples are available for each condition.
11	Deep Factorised Inverse-Sketching	Kaiyue Pang, Da Li, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales	In this paper we study this sketching process and attempt to invert it.
12	Separating Reflection and Transmission Images in the Wild	Patrick Wieschollek, Orazio Gallo, Jinwei Gu, Jan Kautz	We present a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance, which explicitly uses the polarization properties of light.
13	Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions	Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu	In this paper, for data-free scenarios, we propose a novel approach that emulates the effect of data samples with class impressions in order to craft UAPs using data-driven objectives.
14	Rendering Portraitures from Monocular Camera and Beyond	Xiangyu Xu, Deqing Sun, Sifei Liu, Wenqi Ren, Yu-Jin Zhang, Ming-Hsuan Yang, Jian Sun	In this work, we introduce an automatic system that achieves portrait DoF rendering for monocular cameras.
15	Object Level Visual Reasoning in Videos	Fabien Baradel, Natalia Neverova, Christian Wolf, Julien Mille, Greg Mori	We propose a model capable of learning to reason about semantically meaningful spatio-temporal interactions in videos.
16	Dense Pose Transfer	Natalia Neverova, Riza Alp Guler, Iasonas Kokkinos	In this work we integrate ideas from surface-based modeling with neural synthesis: we propose a combination of surface-based pose estimation and deep generative models that allows us to perform accurate pose transfer, i.e. synthesize a new image of a person based on a single image of that person and the image of a pose donor.
17	Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning	Chenyang Si, Ya Jing, Wei Wang, Liang Wang, Tieniu Tan	In this paper, we propose a novel model with spatial reasoning and temporal stack learning (SR-TSL) for skeleton-based action recognition, which consists of a spatial reasoning network (SRN) and a temporal stack learning network (TSLN).
18	Learning to Segment via Cut-and-Paste	Tal Remez, Jonathan Huang, Matthew Brown	This paper presents a weakly-supervised approach to object instance segmentation.
19	Deep Boosting for Image Denoising	Chang Chen, Zhiwei Xiong, Xinmei Tian, Feng Wu	In this paper, we propose a novel deep boosting framework (DBF) for denoising, which integrates several convolutional networks in a feed-forward fashion.
20	Fictitious GAN: Training GANs with Historical Models	Hao Ge, Yin Xia, Xu Chen, Randall Berry, Ying Wu	Inspired by the fictitious play learning process, a novel training method, referred to as Fictitious GAN, is introduced.
21	Self-Supervised Relative Depth Learning for Urban Scene Understanding	Huaizu Jiang, Gustav Larsson, Michael Maire Greg Shakhnarovich, Erik Learned-Miller	In this work, we start by training a deep network, using fully automatic supervision, to predict relative scene depth from single images.
22	Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss	Jianbo Jiao, Ying Cao, Yibing Song, Rynson Lau	In this paper, we investigate the long tail property and delve deeper into the distant depth regions (i.e. the tail part) to propose an attention-driven loss for the network supervision.
23	Bi-box Regression for Pedestrian Detection and Occlusion Estimation	Chunluan Zhou, Junsong Yuan	In this paper, we propose a novel approach to simultaneous pedestrian detection and occlusion estimation by regressing two bounding boxes to localize the full body as well as the visible part of a pedestrian respectively.
24	C-WSL: Count-guided Weakly Supervised Localization	Mingfei Gao, Ang Li, Ruichi Yu, Vlad I. Morariu, Larry S. Davis	We introduce count-guided weakly supervised localization (C-WSL), an approach that uses per-class object count as a new form of supervision to improve weakly supervised localization (WSL).
25	Convolutional Networks with Adaptive Inference Graphs	Andreas Veit, Serge Belongie	In this work, we propose convolutional networks with adaptive inference graphs (ConvNet-AIG) that adaptively define their network topology conditioned on the input image.
26	Summarizing First-Person Videos from Third Persons’ Points of View	HSUAN-I HO, Wei-Chen Chiu, Yu-Chiang Frank Wang	With the goal of deriving an effective model to summarize first-person videos, we propose a novel deep neural network architecture for describing and discriminating vital spatiotemporal information across videos with different points of view.
27	Programmable Triangulation Light Curtains	Jian Wang, Joseph Bartels, William Whittaker, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan	We introduce a novel device that monitors the presence of objects on a virtual shell near the device, which we refer to as a light curtain.
28	Learning Single-View 3D Reconstruction with Limited Pose Supervision	Guandao Yang, Yin Cui, Serge Belongie, Bharath Hariharan	We present a unified framework that can combine both types of supervision: a small amount of camera pose annotations are used to enforce pose-invariance and view-point consistency, and unlabeled images combined with an adversarial loss are used to enforce the realism of rendered, generated models.
29	Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification	T M Feroz Ali, Subhasis Chaudhuri	In this paper we propose a novel metric learning framework called Nullspace Kernel Maximum Margin Metric Learning (NK3ML) which efficiently addresses the small sample size (SSS) problem inherent in person re-identification and offers a significant performance gain over existing state-of-the-art methods.
30	Snap Angle Prediction for 360° Panoramas	Bo Xiong, Kristen Grauman	To discover the relationship between these optimal emph{snap angles} and the spherical panorama’s content, we develop a reinforcement learning approach for the cubemap projection model.
31	Memory Aware Synapses: Learning what (not) to forget	Rahaf Aljundi, Francesca Babiloni , Mohamed Elhoseiny, Marcus Rohrbach, Tinne Tuytelaars	In this paper, we argue that, given the limited model capacity and the unlimited new information to be learned, knowledge has to be preserved or erased selectively.
32	Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks	Adria Recasens, Petr Kellnhofer, Simon Stent, Wojciech Matusik, Antonio Torralba	We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task.
33	Weakly- and Semi-Supervised Panoptic Segmentation	Qizhu Li, Anurag Arnab, Philip H.S. Torr	We present a weakly supervised model that jointly performs both semantic- and instance-segmentation — a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks.
34	K-convexity shape priors for segmentation	Hossam Isack, Lena Gorelick, Karin Ng, Olga Veksler, Yuri Boykov	As shown in the paper, for many forms of convexity our regularization model is significantly more descriptive for any given k.
35	Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images	Nanyang Wang, Yinda Zhang, Zhuwen Li, Yanwei Fu, Wei Liu, Yu-Gang Jiang	We propose an end-to-end deep learning architecture that produces a 3D shape in triangular mesh from a single color image.
36	Boosted Attention: Leveraging Human Attention for Image Captioning	Shi Chen, Qi Zhao	Inspired by the human visual system which is driven by not only the task-specific top-down signals but also the visual stimuli, we in this work propose to use both types of attention for image captioning.
37	Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering	Tianshu Yu, Junchi Yan, Wei Liu, Baoxin Li	In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint.
38	Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence	Shao-Hua Sun, Minyoung Huh, Yuan-Hong Liao, Ning Zhang, Joseph J. Lim	In this paper, we address the task of multi-view novel view synthesis, where we are interested in synthesizing a target image with an arbitrary camera pose from given source images.
39	Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation	Markus Oberweger, Mahdi Rad, Vincent Lepetit	We introduce a novel method for robust and accurate 3D object pose estimation from a single color image under large occlusions.
40	Image Inpainting for Irregular Holes Using Partial Convolutions	Guilin Liu, Fitsum A. Reda, Kevin J. Shih, Ting-Chun Wang, Andrew Tao, Bryan Catanzaro	We propose to use partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels.
41	Audio-Visual Scene Analysis with Self-Supervised Multisensory Features	Andrew Owens, Alexei A. Efros	In this paper, we argue that the visual and audio components of a video signal should be modeled jointly using a fused multisensory representation.
42	Fighting Fake News: Image Splice Detection via Learned Self-Consistency	Minyoung Huh, Andrew Liu, Andrew Owens, Alexei A. Efros	In this paper, we introduce a self-supervised method for learning to detect a visual manipulations using only unlabeled data.
43	End-to-End Joint Semantic Segmentation of Actors and Actions in Video	Jingwei Ji, Shyamal Buch, Alvaro Soto, Juan Carlos Niebles	In this work, we propose a new end-to-end architecture for tackling this task in videos.
44	Visual Text Correction	Amir Mazaheri, Mubarak Shah	In this research, we study a new scenario in which both the sentence and the video are given, but the sentence is inaccurate. This paper introduces a new problem, called Visual Text Correction (VTC), i.e., finding and replacing an inaccurate word in the textual description of a video.
45	Deep Co-Training for Semi-Supervised Image Recognition	Siyuan Qiao, Wei Shen, Zhishuai Zhang, Bo Wang, Alan Yuille	In this paper, we study the problem of semi-supervised image recognition, which is to learn classifiers using both labeled and unlabeled images.
46	Progressive Neural Architecture Search	Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy	We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms.
47	Explainable Neural Computation via Stack Neural Module Networks	Ronghang Hu, Jacob Andreas, Trevor Darrell, Kate Saenko	In this paper, we present a novel neural modular approach that performs compositional reasoning by automatically inducing a desired sub-task decomposition without relying on strong supervision.
48	Attributes as Operators: Factorizing Unseen Attribute-Object Compositions	Tushar Nagarajan, Kristen Grauman	We present a new approach to modeling visual attributes.
49	Scalable Exemplar-based Subspace Clustering on Class-Imbalanced Data	Chong You, Chi Li, Daniel P. Robinson, Rene Vidal	This paper presents an exemplar-based subspace clustering method to tackle the problem of imbalanced and large-scale datasets.
50	RCAA: Relational Context-Aware Agents for Person Search	Xiaojun Chang, Po-Yao Huang, Yi-Dong Shen, Xiaodan Liang, Yi Yang, Alexander G. Hauptmann	In this paper, we address this problem by training relational context-aware agents which learn the actions to localize the target person from the gallery of whole scene images.
51	Product Quantization Network for Fast Image Retrieval	Tan Yu, Junsong Yuan, Chen Fang, Hailin Jin	By extending the hard assignment to soft assignment, we make it feasible to incorporate the product quantization as a layer of a convolutional neural network and propose our product quantization network.
52	Hand Pose Estimation via Latent 2.5D Heatmap Regression	Umar Iqbal, Pavlo Molchanov, Thomas Breuel Juergen Gall, Jan Kautz	In this paper we propose a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation.
53	Multimodal Unsupervised Image-to-image Translation	Xun Huang, Ming-Yu Liu, Serge Belongie, Jan Kautz	To address this limitation, we propose a Multimodal Unsupervised Image-to-image Translation (MUNIT) framework.
54	Depth-aware CNN for RGB-D Segmentation	Weiyue Wang, Ulrich Neumann	To address these issues, we present Depth-aware CNN by introducing two intuitive, flexible and effective operations: depth-aware convolution and depth-aware average pooling.
55	Visual Coreference Resolution in Visual Dialog using Neural Module Networks	Satwik Kottur, Jose M. F. Moura, Devi Parikh, Dhruv Batra, Marcus Rohrbach	In this work, we propose a neural module network architecture for visual dialog by introducing two novel modules—Refer and Exclude—that perform explicit, grounded, coreference resolution at a finer word level.
56	Learning Blind Video Temporal Consistency	Wei-Sheng Lai, Jia-Bin Huang, Oliver Wang, Eli Shechtman, Ersin Yumer, Ming-Hsuan Yang	In this paper, we present an efficient end-to-end approach based on deep recurrent network for enforcing temporal consistency in a video.Our method takes the original unprocessed and per-frame processed videos as inputs to produce a temporally consistent video.Consequently, our approach is agnostic to specific image processing algorithms applied on the original video.We train the proposed network by minimizing both short-term and long-term temporal losses as well as the perceptual loss to strike a balance between temporal stability and perceptual similarity with the processed frames.At test time, our model does not require computing optical flow and thus achieves real-time speed even for high-resolution videos.
57	Diverse Image-to-Image Translation via Disentangled Representations	Hsin-Ying Lee, Hung-Yu Tseng, Jia-Bin Huang, Maneesh Singh, Ming-Hsuan Yang	In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images.
58	Learning to Blend Photos	Wei-Chih Hung, Jianming Zhang, Xiaohui Shen, Zhe Lin, Joon-Young Lee, Ming-Hsuan Yang	To make photo blending accessible to general public, we propose an efficient approach for automatic photo blending via deep learning.
59	Switchable Temporal Propagation Network	Sifei Liu, Guangyu Zhong, Shalini De Mello, Jinwei Gu, Varun Jampani, Ming-Hsuan Yang, Jan Kautz	In this paper, we propose a learnable unified framework for propagating a variety of visual properties of video images, including but not limited to color, high dynamic range (HDR), and segmentation mask, where the properties are available for only a few key-frames.
60	Deeply Learned Compositional Models for Human Pose Estimation	Wei Tang, Pei Yu, Ying Wu	To address these issues, this paper introduces a novel framework, termed as Deeply Learned Compositional Model (DLCM), for HPE.
61	Unsupervised Video Object Segmentation with Motion-based Bilateral Networks	Siyang Li, Bryan Seybold, Alexey Vorobyov, Xuejing Lei, C.-C. Jay Kuo	In this work, we study the unsupervised video object segmentation problem where moving objects are segmented without prior knowledge of these objects.
62	CornerNet: Detecting Objects as Paired Keypoints	Hei Law, Jia Deng	We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network.
63	Unsupervised holistic image generation from key local patches	Donghoon Lee, Sangdoo Yun, Sungjoon Choi, Hwiyeon Yoo, Ming-Hsuan Yang, Songhwai Oh	In this work, key local patches are defined as informative regions of the target object or scene. We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior.
64	Group Normalization	Yuxin Wu, Kaiming He	In this paper, we present Group Normalization (GN) as a simple alternative to BN.
65	Generalizing A Person Retrieval Model Hetero- and Homogeneously	Zhun Zhong, Liang Zheng, Shaozi Li, Yi Yang	To this end, we introduce a Hetero-Homogeneous Learning (HHL) method.
66	CAR-Net: Clairvoyant Attentive Recurrent Network	Amir Sadeghian, Ferdinand Legros, Maxime Voisin, Ricky Vesel, Alexandre Alahi, Silvio Savarese	We present an interpretable framework for path prediction that leverages dependencies between agents’ behaviors and their spatial navigation environment. To study the impact of space on agents’ trajectories, we build a new dataset made of top-view images of hundreds of scenes (Formula One racing tracks) where agents’ behaviors are heavily influenced by known areas in the images (e.g., upcoming turns).
67	Cross-Modal Hamming Hashing	Yue Cao , Bin Liu, Mingsheng Long, Jianmin Wang	This work presents Cross-Modal Hamming Hashing (CMHH), a novel deep cross-modal hashing approach that generates compact and highly concentrated hash codes to enable efficient and effective Hamming space retrieval.
68	PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction	Yifei Shi, Kai Xu, Matthias Niessner, Szymon Rusinkiewicz, Thomas Funkhouser	We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction.
69	DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency	Yuliang Zou, Zelun Luo, Jia-Bin Huang	We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences.
70	Distractor-aware Siamese Networks for Visual Object Tracking	Zheng Zhu, Qiang Wang, Bo Li, Wei Wu, Junjie Yan, Weiming Hu	In this paper, we focus on learning distractor-aware Siamese networks for accurate and long-term tracking.
71	Multiresolution Tree Networks for 3D Point Cloud Processing	Matheus Gadelha, Rui Wang, Subhransu Maji	We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks.
72	Propagating LSTM: 3D Pose Estimation based on Joint Interdependency	Kyoungoh Lee, Inwoong Lee, Sanghoon Lee	We present a novel 3D pose estimation method based on joint interdependency (JI) for acquiring 3D joints from the human pose of an RGB image.
73	Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A Convolutional Neural Aggregation Network	Woojae Kim, Jongyoo Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee	In this paper, we propose a novel full-reference (FR) VQA framework named Deep Video Quality Assessor (DeepVQA) to quantify the spatio-temporal visual perception via a convolutional neural network (CNN) and a convolutional neural aggregation network (CNAN).
74	Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground	Deng-Ping Fan, Ming-Ming Cheng, Jiang-Jiang Liu, Shang-Hua Gao, Qibin Hou, Ali Borji	We provide a comprehensive evaluation of salient object detection (SOD) models. Then, we propose a new high-quality dataset and update the previous saliency benchmark.
75	Face Recognition with Contrastive Convolution	Chunrui Han, Shiguang Shan, Meina Kan, Shuzhe Wu, Xilin Chen	Inspired, we propose a novel CNN structure with what we referred to as contrastive convolution, which specifically focuses on the distinct characteristics between the two faces to compare, i.e., those contrastive characteristics.
76	Monocular Depth Estimation with Affinity, Vertical Pooling, and Label Enhancement	Yukang Gan, Xiangyu Xu, Wenxiu Sun, Liang Lin	In the proposed algorithm we introduce vertical pooling to aggregate image features vertically to improve the depth accuracy.Furthermore, since the Lidar depth ground truth is quite sparse, we enhance the depth labels by generating high-quality dense depth maps with off-the-shelf stereo matching method which takes left-right image pairs as input.We also integrate multi-scale structures in our network to obtain global understanding the image depth and exploit residual learning to help depth refinement.We demonstrate that the proposed algorithm performs favorably against state-of-the-art methods both qualitatively and quantitatively on the KITTI driving dataset.
77	Domain Adaptation through Synthesis for Unsupervised Person Re-identification	Slawomir Bak, Peter Carr, Jean-Francois Lalonde	To achieve better accuracy in unseen illumination conditions we propose a novel domain adaptation technique that takes advantage of our synthetic data and performs fine-tuning in a completely unsupervised way. To alleviate this problem, we introduce a new synthetic dataset that contains hundreds of illumination conditions.
78	Adding Attentiveness to the Neurons in Recurrent Neural Networks	Pengfei Zhang, Jianru Xue, Cuiling Lan, Wenjun Zeng, Zhanning Gao, Nanning Zheng	We propose adding a simple yet effective Element-wise-Attention Gate (EleAttG) to an RNN block (e.g., all RNN neurons in a network layer) that empowers the RNN neurons to have the attentiveness capability.
79	Neural Stereoscopic Image Style Transfer	Xinyu Gong, Haozhi Huang, Lin Ma, Fumin Shen, Wei Liu, Tong Zhang	In this paper, we propose a novel dual path network for view-consistent style transfer on stereoscopic images.
80	Learning Dynamic Memory Networks for Object Tracking	Tianyu Yang, Antoni B. Chan	In this paper, we propose a dynamic memory network to adapt the template to the target’s appearance variations during tracking.
81	Gray-box Adversarial Training	B. S. Vivek, Konda Reddy Mopuri, R. Venkatesh Babu	In this paper we, (i) demonstrate the drawbacks of existing evaluation policy, (ii) Introduce novel variants of white-box and black-box attacks, dubbed “gray-box adversarial attacks” based on which we propose novel evaluation method to assess the robustness of the learned models, and (iii) propose a novel variant of adversarial training, named “Graybox Adversarial Training” that uses intermediate versions of the models to seed the adversaries.
82	GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints	Zixin Luo, Tianwei Shen, Lei Zhou, Siyu Zhu, Runze Zhang, Yao Yao, Tian Fang, Long Quan	In this paper, we mitigate this limitation by proposing a novel local descriptor learning approach that integrates geometry constraints from multi-view reconstructions, which benefit the learning process in data generation, data sampling and loss computation.
83	Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks	Minjun Li, Haozhi Huang, Lin Ma, Wei Liu, Tong Zhang, Yugang Jiang	In this paper, we propose novel Stacked Cycle-Consistent Adversarial Networks (SCANs) by decomposing a single translation into multi-stage transformations, which not only boost the image translation quality but also enable higher resolution image-toimage translation in a coarse-to-fine fashion.
84	Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling	Hiroaki Santo, Michael Waechter, Masaki Samejima, Yusuke Sugano, Yasuyuki Matsushita	We present a practical method for geometric point light source calibration.
85	Find and Focus: Retrieve and Localize Video Events with Natural Language Queries	Dian Shao, Yu Xiong, Yue Zhao, Qingqiu Huang, Yu Qiao, Dahua Lin	In this work, we aim to move beyond this limitation by delving into the internal structures of both sides, the queries and the videos.
86	Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane	Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng	Inspired by the pioneering work of information bottleneck principle for Deep Neural Networks (DNNs) analysis, we design an information plane based framework to evaluate the capability of DNNs for image classification tasks, which not only helps understand the capability of DNNs, but also helps us choose a neural network which leads to higher classification accuracy more efficiently.
87	Super-Identity Convolutional Neural Network for Face Hallucination	Kaipeng Zhang, Zhanpeng Zhang, Chia-Wen Cheng, Winston H. Hsu, Yu Qiao, Wei Liu, Tong Zhang	To overcome this challenge, we present a domain-integrated training approach by constructing a robust identity metric for faces from these two domains.
88	SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network	Yancheng Bai, Yongqiang Zhang, Mingli Ding, Bernard Ghanem	To deal with small object detection problem, we propose an end-to-end multi-task generative adversarial network (MTGAN).
89	Face Super-resolution Guided by Facial Component Heatmaps	Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, Richard Hartley	State-of-the-art face super-resolution methods use deep convolutional neural networks to learn a mapping between low-resolution (LR) facial patterns and their corresponding high-resolution (HR) counterparts by exploring local information.
90	ML-LocNet: Improving Object Localization with Multi-view Learning Network	Xiaopeng Zhang, Yang Yang, Jiashi Feng	We propose a Multi-view Learning Localization Network (ML-LocNet) by incorporating multi-view learning into a two-phase WSOL model.
91	Facial Expression Recognition with Inconsistently Annotated Datasets	Jiabei Zeng, Shiguang Shan, Xilin Chen	To address the inconsistency, we propose an Inconsistent Pseudo Annotations to Latent Truth(IPA2LT) framework to train a FER model from multiple inconsistently labeled datasets and large scale unlabeled data.
92	Visual Question Answering as a Meta Learning Task	Damien Teney, Anton van den Hengel	We propose instead to approach VQA as a meta learning task, thus separating the question answering method from the information required.
93	Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition	Junwu Weng, Mengyuan Liu, Xudong Jiang, Junsong Yuan	Rather than directly representing the 3D pose using its joint locations, in this paper, we propose Deformable Pose Traversal Convolution which applies one-dimensional convolution to traverse the 3D pose to represent it.
94	Semi-Dense 3D Reconstruction with a Stereo Event Camera	Yi Zhou, Guillermo Gallego, Henri Rebecq, Laurent Kneip, Hongdong Li, Davide Scaramuzza	This paper presents a solution to the problem of 3D reconstruction from data captured by a stereo event-camera rig moving in a static scene, such as in the context of stereo Simultaneous Localization and Mapping.
95	What do I Annotate Next? An Empirical Study of Active Learning for Action Localization	Fabian Caba Heilbron, Joon-Young Lee, Hailin Jin, Bernard Ghanem	In this paper, we introduce a novel active learning framework for temporal localization that aims to mitigate this data dependency issue.
96	HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning	Thomas Robert, Nicolas Thome, Matthieu Cord	In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet.
97	Self-Calibrating Isometric Non-Rigid Structure-from-Motion	Shaifali Parashar, Adrien Bartoli, Daniel Pizarro	We present self-calibrating isometric non-rigid structure- from-motion (SCIso-NRSfM), the first method to reconstruct a non-rigid object from at least three monocular images with constant but unknown focal length.
98	Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields	Yongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, Dacheng Tao, Mingli Song	In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control.
99	Reverse Attention for Salient Object Detection	Shuhan Chen, Xiuli Tan, Ben Wang, Xuelong Hu	To this end, this paper presents an accurate yet compact deep network for efficient salient object detection.
100	Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization	Humam Alwassel, Fabian Caba Heilbron, Bernard Ghanem	To address this need, we propose the new problem of action spotting in video, which we define as finding a specific action in a video while observing a small portion of that video.
101	Diagnosing Error in Temporal Action Detectors	Humam Alwassel, Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem	To this end, we introduce a new diagnostic tool to analyze the performance of temporal action detectors in videos and compare different methods beyond a single scalar metric.
102	Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation	Helge Rhodin, Mathieu Salzmann, Pascal Fua	In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations.
103	Massively Parallel Video Networks	Joao Carreira, Viorica Patraucean, Laurent Mazare, Andrew Zisserman, Simon Osindero	We introduce a class of causal video understanding models that aims to improve efficiency of video processing by maximising throughput, minimising latency, and reducing the number of clock cycles.
104	Transductive Centroid Projection for Semi-supervised Large-scale Recognition	Yu Liu, Guanglu Song, Jing Shao, Xiao Jin, Xiaogang Wang	Specifically, we design the TCP module by dynamically adding an extit{ad hoc anchor} for each cluster in one mini-batch.
105	PSANet: Point-wise Spatial Attention Network for Scene Parsing	Hengshuang Zhao, Yi Zhang, Shu Liu, Jianping Shi, Chen Change Loy, Dahua Lin, Jiaya Jia	In this paper, we propose the point-wise spatial attention network (PSANet) to relax the local neighborhood constraint.
106	Robust Anchor Embedding for Unsupervised Video Person Re-Identification in the Wild	Mang Ye, Xiangyuan Lan, Pong C. Yuen	To achieve it, we propose a novel Robust AnChor Embedding (RACE) framework via deep feature representation learning for large-scale unsupervised video re-ID.
107	Semi-Supervised Deep Learning with Memory	Yanbei Chen, Xiatian Zhu, Shaogang Gong	In this work, we propose a novel Memory-Assisted Deep Neural Network (MA-DNN) capable of exploiting the memory of model learning to enable semi-supervised learning.
108	Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline	Zhenbo Xu, Wei Yang, Ajin Meng, Nanxue Lu, Huan Huang, Changchun Ying, Liusheng Huang	In this paper, we introduce CCPD, a large and comprehensive LP dataset.
109	Repeatability Is Not Enough: Learning Affine Regions via Discriminability	Dmytro Mishkin, Filip Radenovic, Jiri Matas	A method for learning local affine-covariant regions is presented.
110	Learning Warped Guidance for Blind Face Restoration	Xiaoming Li, Ming Liu, Yuting Ye, Wangmeng Zuo, Liang Lin, Ruigang Yang	For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network (GFRNet).
111	Compressing the Input for CNNs with the First-Order Scattering Transform	Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko, Michal Valko	We subsequently apply our Imagenet trained hybrid model as a base model on a detection system, which typically has larger image inputs.
112	Face De-Spoofing: Anti-Spoofing via Noise Modeling	Amin Jourabloo, Yaojie Liu, Xiaoming Liu	In this work, motivated by the noise modeling and denoising algorithms, we identify a new problem of face de-spoofing, for the purpose of anti-spoofing: inversely decomposing a spoof face into a spoof noise and a live face, and then utilizing the spoof noise for classification.
113	Faces as Lighting Probes via Unsupervised Deep Highlight Extraction	Renjiao Yi, Chenyang Zhu, Ping Tan, Stephen Lin	We present a method for estimating detailed scene illumination using human faces in a single image.
114	Unsupervised Hard Example Mining from Videos for Improved Object Detection	SouYoung Jin, Aruni RoyChowdhury, Huaizu Jiang, Ashish Singh, Aditya Prasad, Deep Chakraborty, Erik Learned-Miller	In this work, we show how large numbers of hard negatives can be obtained {em automatically} by analyzing the output of a trained detector on video sequences.
115	On Offline Evaluation of Vision-based Driving Models	Felipe Codevilla, Antonio M. Lopez, Vladlen Koltun, Alexey Dosovitskiy	In this paper, we investigate the relation between various online and offline metrics for evaluation of autonomous driving models.
116	Deep Fundamental Matrix Estimation	Rene Ranftl, Vladlen Koltun	We present an approach to robust estimation of fundamental matrices from noisy data contaminated by outliers.
117	ContextVP: Fully Context-Aware Video Prediction	Wonmin Byeon, Qin Wang, Rupesh Kumar Srivastava, Petros Koumoutsakos	To address this issue, we introduce a fully context-aware architecture that captures the entire available past context for each pixel using Parallel Multi-Dimensional LSTM units and aggregates it using blending units.
118	Visual Psychophysics for Making Face Recognition Algorithms More Explainable	Brandon RichardWebster, So Yon Kwon, Christopher Clarizio, Samuel E. Anthony, Walter J. Scheirer	In this paper, we suggest that visual psychophysics is a viable methodology for making face recognition algorithms more explainable.
119	TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild	Matthias Muller, Adel Bibi, Silvio Giancola, Salman Alsubaihi, Bernard Ghanem	In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset.
120	Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image	Siyuan Huang, Siyuan Qi, Yixin Zhu, Yinxue Xiao, Yuanlu Xu, Song-Chun Zhu	We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model.
121	Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model	Baris Gecer, Binod Bhattarai, Josef Kittler, Tae-Kyun Kim	We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with a wide range of expressions, poses, and illuminations conditioned by synthetic images sampled from a 3D morphable model.
122	Improved Structure from Motion Using Fiducial Marker Matching	Joseph DeGol, Timothy Bretl, Derek Hoiem	In this paper, we present an incremental structure from motion (SfM) algorithm that signiﬁcantly outperforms existing algorithms when ﬁducial markers are present in the scene, and that matches the performance of existing algorithms when no markers are present. To validate our algorithm, we introduce a new dataset with 16 image collections of large indoor scenes with challenging characteristics (e.g., blank hallways, glass facades, brick walls) and with markers placed throughout.
123	Conditional Prior Networks for Optical Flow	Yanchao Yang, Stefano Soatto	We introduce a novel architecture, called Conditional Prior Network (CPN), and show how to train it to yield a conditional prior.
124	Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training	Yang Zou, Zhiding Yu, B.V.K. Vijaya Kumar, Jinsong Wang	In this paper, we propose a novel UDA frameworkbased on an iterative self-training (ST) procedure, where the problemis formulated as latent variable loss minimization, and can be solved byalternatively generating pseudo labels on target data and re-training themodel with these labels.
125	DetNet: Design Backbone for Object Detection	Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun	Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection.
126	BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation	Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang	In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet).
127	HairNet: Single-View Hair Reconstruction using Convolutional Neural Networks	Yi Zhou, Liwen Hu, Jun Xing, Weikai Chen, Han-Wei Kung, Xin Tong, Hao Li	We introduce a deep learning-based method to generate full 3D hair geometry from an unconstrained image.
128	Neural Network Encapsulation	Hongyang Li, Xiaoyang Guo, Bo DaiWanli Ouyang, Xiaogang Wang	To resolve this limitation, we approximate the routing process with two branches: a master branch which collects primary information from its direct contact in the lower layer and an aide branch that replenishes master based on pattern variants encoded in other lower capsules.
129	StarMap for Category-Agnostic Keypoint and Viewpoint Estimation	Xingyi Zhou, Arjun Karpur, Linjie Luo, Qixing Huang	We propose a category-agnostic keypoint representation, which combines a multi-peak heatmap (StarMap) for all the keypoints and their corresponding features as 3D locations in the canonical viewpoint (CanViewFeature) defined for each instance.
130	Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation	Yikang Li, Wanli Ouyang, Bolei Zhou, Jianping Shi, Chao Zhang, Xiaogang Wang	To improve the efficiency of scene graph generation, we propose a subgraph-based connection graph to concisely represent the scene graph during the inference.
131	Multi-Fiber Networks for Video Recognition	Yunpeng Chen, Yannis Kalantidis, Jianshu Li, Shuicheng Yan, Jiashi Feng	In this paper, we aim to reduce the computational cost of spatio-temporal deep neural networks, making them run as fast as their 2D counterparts while preserving state-of-the-art accuracy on video recognition benchmarks.
132	Towards Human-Level License Plate Recognition	Jiafan Zhuang, Saihui Hou, Zilei Wang, Zheng-Jun Zha	In this paper, we propose a novel LPR framework consisting of semantic segmentation and character counting, towards achieving human-level performance.
133	Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition	Guojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao, Chen Change Loy	Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
134	Generalized Loss-Sensitive Adversarial Learning with Manifold Margins	Marzieh Edraki, Guo-Jun Qi	Thus, we define a pullback operator to map samples back to their data manifold, and a manifold margin is defined as the distance between the pullback representations to distinguish between real and fake sam- ples and learn the optimal generators.
135	Pose Proposal Networks	Taiki Sekii	We propose a novel method to detect an unknown number of articulated 2D poses in real time.
136	Less is More: Picking Informative Frames for Video Captioning	Yangyu Chen, Shuhui Wang, Weigang Zhang, Qingming Huang	We propose a plug-and-play PickNet to perform informative frame picking in video captioning.
137	Robust Optical Flow in Rainy Scenes	Ruoteng Li, Robby T. Tan, Loong-Fah Cheong	To resolve the problem, we introduce a residue channel, a single channel (gray) image that is free from rain, and its colored version, a colored-residue image. We also provide an optical flow dataset consisting of both synthetic and real rain images.
138	Into the Twilight Zone: Depth Estimation using Joint Structure-Stereo Optimization	Aashish Sharma, Loong-Fah Cheong	We present a joint Structure-Stereo optimization model that is robust for disparity estimation under low-light conditions.
139	Structured Siamese Network for Real-Time Visual Tracking	Yunhua Zhang, Lijun Wang, Jinqing Qi, Dong Wang, Mengyang Feng, Huchuan Lu	In this paper, we circumvent this issue by proposing a local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking.
140	Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation	Ruochen Fan, Qibin Hou, Ming-Ming Cheng, Gang Yu, Ralph R. Martin, Shi-Min Hu	In this paper, we use an instance-level salient object detector to automatically generate salient instances (candidate objects) for training images.
141	Learning Deep Representations with Probabilistic Knowledge Transfer	Nikolaos Passalis, Anastasios Tefas	In this paper we propose a novel probabilistic knowledge transfer method that works by matching the probability distribution of the data in the feature space instead of their actual representation.
142	Recycle-GAN: Unsupervised Video Retargeting	Aayush Bansal, Shugao Ma, Deva Ramanan, Yaser Sheikh	We introduce a data-driven approach for unsupervised video retargeting that translates content from one domain to another while preserving the style native to a domain, i.e., if contents of John Oliver’s speech were to be transferred to Stephen Colbert, then the generated content/speech should be in Stephen Colbert’s style.
143	Escaping from Collapsing Modes in a Constrained Space	Chia-Che Chang, Chieh Hubert Lin, Che-Rung Lee, Da-Cheng Juan, Wei Wei, Hwann-Tzong Chen	We propose a new model, called BEGAN with a Constrained Space (BEGAN-CS), which includes a latent-space constraint in the loss function.
144	Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal Alignment	Shervin Ardeshir, Ali Borji	In this paper, we aim to relate these two sources of information from a surveillance standpoint, namely in terms of identification and temporal alignment.
145	Cross-Modal and Hierarchical Modeling of Video and Text	Bowen Zhang, Hexiang Hu, Fei Sha	In this paper, we investigate the modeling techniques for such hierarchical sequential data where there are correspondences across multiple modalities.
146	Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset	Qi Guo, Iuri Frosio, Orazio Gallo, Todd Zickler, Jan Kautz	We propose a two-stage, deep-learning approach to address all of these sources of artifacts simultaneously.
147	Visual-Inertial Object Detection and Mapping	Xiaohan Fei, Stefano Soatto	We present a method to populate an unknown environment with models of previously seen objects, placed in a Euclidean reference frame that is inferred causally and on-line using monocular video along with inertial sensors. We test our algorithm on existing datasets, and also introduce the VISMA dataset, that provides ground truth pose, point-cloud map, and object models, along with time-stamped inertial measurements.
148	Zero-Shot Object Detection	Ankan Bansal, Karan Sikka, Gaurav Sharma, Rama Chellappa, Ajay Divakaran	We present a principled approach by first adapting visual-semantic embeddings for ZSD. We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training.
149	Tracking Emerges by Colorizing Videos	Carl Vondrick, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy	We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision.
150	Actor-centric Relation Network	Chen Sun, Abhinav Shrivastava, Carl Vondrick, Kevin Murphy, Rahul Sukthankar, Cordelia Schmid	We show that ACRN outperforms alternative approaches which capture relation information, and that the proposed framework improves upon the state-of-the-art performance on JHMDB and AVA.
151	Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification	Saining Xie, Chen Sun, Jonathan Huang, Zhuowen Tu, Kevin Murphy	We seek a balance between speed and accuracy by building an effective and efficient video classification system through systematic exploration of critical network design choices.
152	SkipNet: Learning Dynamic Routing in Convolutional Networks	Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, Joseph E. Gonzalez	We formulate the dynamic skipping problem in the context of sequential decision making and propose a hybrid learning algorithm that combines supervised learning and reinforcement learning to address the challenges of non-differentiable skipping decisions.
153	Quantized Densely Connected U-Nets for Efficient Landmark Localization	Zhiqiang Tang, Xi Peng, Shijie Geng, Lingfei Wu, Shaoting Zhang, Dimitris Metaxas	In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization.
154	Person Search in Videos with One Portrait Through Visual and Temporal Links	Qingqiu Huang, Wentao Liu, Dahua Lin	In this paper, we aim to tackle this challenge and propose a novel framework, which takes into account the identity invariance along a tracklet, thus allowing person identities to be propagated via both the visual and the temporal links. To promote the study of person search, we construct a large-scale benchmark, which contains 127K manually annotated tracklets from 192 movies.
155	HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs	Zerong Zheng, Tao Yu, Hao Li, Kaiwen Guo, Qionghai Dai, Lu Fang, Yebin Liu	We propose a light-weight and highly robust real-time human performance capture method based on a single depth camera and sparse inertial measurement units (IMUs).
156	Variational Wasserstein Clustering	Liang Mi, Wen Zhang, Xianfeng Gu, Yalin Wang	We propose a new clustering method based on optimal transportation.
157	A Modulation Module for Multi-task Learning with Applications in Image Retrieval	Xiangyun Zhao, Haoxiang Li, Xiaohui Shen, Xiaodan Liang, Ying Wu	To address the this problem, we propose a general modulation module, which can be inserted into any convolutional neural network architecture, to encourage the coupling and feature sharing of relevant tasks while disentangling the learning of irrelevant tasks with minor parameters addition.
158	Learning Human-Object Interactions by Graph Parsing Neural Networks	Siyuan Qi, Wenguan Wang, Baoxiong Jia, Jianbing Shen, Song-Chun Zhu	We introduce the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being differentiable end-to-end.
159	Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data	Xihui Liu, Hongsheng Li, Jing Shao, Dapeng Chen, Xiaogang Wang	In this work, we propose an image captioning framework with a self-retrieval module as training guidance, which encourages generating discriminative captions.
160	Decouple Learning for Parameterized Image Operators	Qingnan Fan, Dongdong Chen, Lu Yuan, Gang Hua, Nenghai Yu, Baoquan Chen	To overcome this limitation, we propose a new decouple learning algorithm to learn from the operator parameters to dynamically adjust the weights of a deep network for image operators, denoted as the base network.
161	Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification	Xing Wei, Yue Zhang, Yihong Gong, Jiawei Zhang, Nanning Zheng	Motivated by this point, we advocate an alternative pooling method which transforms the CNN feature matrix to an orthonormal matrix consists of its principal singular vectors.
162	Liquid Pouring Monitoring via Rich Sensory Inputs	Tz-Ying Wu, Juan-Ting Lin, Tsun-Hsuang Wang, Chan-Wei Hu, Juan Carlos Niebles, Min Sun	In this work, we take liquid pouring as a concrete example and aim at learning to continuously monitor whether liquid pouring is successful (e.g., no spilling) or not via rich sensory inputs.
163	Leveraging Motion Priors in Videos for Improving Human Segmentation	Yu-Ting Chen, Wen-Yen Chang, Hai-Lun Lu, Tingfan Wu, Min Sun	In this work, we propose to leverage “motion prior” in videos for improving human segmentation in a weakly-supervised active learning setting.
164	Triplet Loss in Siamese Network for Object Tracking	Xingping Dong, Jianbing Shen	In this paper, a novel triplet loss is proposed to extract expressive deep feature for object tracking by adding it into Siamese network framework instead of pairwise loss for training.
165	Macro-Micro Adversarial Network for Human Parsing	Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang	To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN).
166	Contour Knowledge Transfer for Salient Object Detection	Xin Li, Fan Yang, Hong Cheng, Wei Liu, Dinggang Shen	Our goal is to overcome this limitation by automatically converting an existing deep contour detection model into a salient object detection model without using any manual salient object masks.
167	Point-to-Point Regression PointNet for 3D Hand Pose Estimation	Liuhao Ge, Zhou Ren, Junsong Yuan	Convolutional Neural Networks (CNNs)-based methods for 3D hand pose estimation with depth cameras usually take 2D depth images as input and directly regress holistic 3D hand pose.
168	Fine-grained Video Categorization with Redundancy Reduction Attention	Chen Zhu, Xiao Tan, Feng Zhou, Xiao Liu, Kaiyu Yue, Errui Ding, Yi Ma	In this paper, we propose a new network structure, known as Redundancy Reduction Attention (RRA), which learns to focus on multiple discriminative patterns by suppressing redundant feature channels. Furthermore, we have collected two large-scale video datasets, YouTube-Birds and YouTube-Cars, for future researches on fine-grained video categorization.
169	Analyzing Clothing Layer Deformation Statistics of 3D Human Motions	Jinlong Yang, Jean-Sebastien Franco, Franck Hetroy-Wheeler, Stefanie Wuhrer	To this purpose we propose a comprehensive analysis of the statistics of this layer with a simple two-component model, based on PCA subspace reduction of the layer information on one hand, and a generic parameter regression model using neural networks on the other hand, designed to regress from any semantic parameter whose variation is observed in a training set, to the layer parameterization space.
170	DOCK: Detecting Objects by transferring Common-sense Knowledge	Krishna Kumar Singh, Santosh Divvala, Ali Farhadi, Yong Jae Lee	We present a scalable approach for Detecting Objects by transferring Common-sense Knowledge (DOCK) from source to target categories.
171	Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining	Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha	We propose a novel deep network architecture based on deep convolutional and recurrent neural networks for single image deraining.
172	Multi-Scale Spatially-Asymmetric Recalibration for Image Classification	Yan Wang, Lingxi Xie, Siyuan Qiao, Ya Zhang, Wenjun Zhang, Alan L. Yuille	This paper addresses this issue by a recalibration process, which refers to the surrounding region of each neuron, computes an importance value and multiplies it to the original neural response.
173	Fast and Accurate Intrinsic Symmetry Detection	Rajendra Nagar, Shanmuganathan Raman	In this work, we detect the intrinsic reflective symmetry in triangle meshes where we have to find the intrinsically symmetric point for each point of the shape.
174	Open Set Domain Adaptation by Backpropagation	Kuniaki Saito, Shohei Yamamoto, Yoshitaka Ushiku, Tatsuya Harada	In this paper, we propose a method for an open set domain adaptation scenario, which utilizes adversarial training.
175	Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance	Ramprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny, Tilak Sharma, Dhruv Batra, Devi Parikh, Stefan Lee	In this work we introduce a simple, efficient zero-shot learning approach based on this observation.
176	CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering	Zhengqi Li, Noah Snavely	To that end, we present CGINTRINSICS, a new, large-scale dataset of physically-based rendered images of scenes with full ground truth decompositions.
177	Stereo Computation for a Single Mixture Image	Yiran Zhong, Yuchao Dai, Hongdong Li	In this work we give a novel deep-learning based solution, by jointly solving the two subtasks of image layer separation as well as stereo matching. This paper proposes an original problem of emph{stereo computation from a single (additive) mixture image}– a challenging problem that had not been researched before.
178	Objects that Sound	Relja Arandjelovic, Andrew Zisserman	In this paper our objectives are, first, networks that can embed audio and visual inputs into a common space that is suitable for cross-modal retrieval; and second, a network that can localize the object that sounds in an image, given the audio signal.
179	Iterative Crowd Counting	Viresh Ranjan, Hieu Le, Minh Hoai	In this work, we tackle the problem of crowd counting in images.
180	Weakly Supervised Region Proposal Network and Object Detection	Peng Tang, Xinggang Wang, Angtian Wang, Yongluan Yan, Wenyu Liu, Junzhou Huang, Alan Yuille	In this paper, we propose a weakly supervised region proposal network which is trained using only image-level annotations.
181	Image Super-Resolution Using Very Deep Residual Channel Attention Networks	Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, Yun Fu	To solve these problems, we propose the very deep residual channel attention networks (RCAN).
182	Dividing and Aggregating Network for Multi-view Action Recognition	Dongang Wang, Wanli Ouyang, Wen Li, Dong Xu	In this paper, we propose a new Dividing and Aggregating Network (DA-Net) for multi-view action recognition.
183	Layer-structured 3D Scene Inference via View Synthesis	Shubham Tulsiani, Richard Tucker, Noah Snavely	We present an approach to infer a layer-structured 3D representation of a scene from a single input image.
184	Deblurring Natural Image Using Super-Gaussian Fields	Yuhang Liu, Wenyong Dong, Dong Gong, Lei Zhang, Qinfeng Shi	To address the above issues, we present a novel image prior for image deblurring based on a Super-Gaussian field model with adaptive structures.
185	Learning Category-Specific Mesh Reconstruction from Image Collections	Angjoo Kanazawa, Shubham Tulsiani, Alexei A. Efros, Jitendra Malik	We present a learning framework for recovering the 3D shape, camera, and texture of an object from a single image.
186	Selective Zero-Shot Classification with Augmented Attributes	Jie Song, Chengchao Shen, Jie Lei, An-Xiang Zeng, Kairi Ou, Dacheng Tao, Mingli Song	In this paper, we introduce a selective zero-shot classification problem: how can the classifier avoid making dubious predictions?
187	Real-time ‘Actor-Critic’ Tracking	Boyu Chen, Dong Wang, Peixia Li, Shuang Wang, Huchuan Lu	In this work, we propose a novel tracking algorithm with real-time performance based on the ‘Actor-Critic’ framework.
188	Zero-Annotation Object Detection with Web Knowledge Transfer	Qingyi Tao, Hao Yang, Jianfei Cai	On the contrary, we propose an object detection method that does not require any form of human annotation on target tasks, by exploiting freely available web images.
189	Question-Guided Hybrid Convolution for Visual Question Answering	Peng Gao, Hongsheng Li, Shuang Li, Pan Lu, Yikang Li, Steven C.H. Hoi, Xiaogang Wang	In this paper, we propose a novel Question-Guided Hybrid Convolution (QGHC) network for Visual Question Answering (VQA).
190	Fully Motion-Aware Network for Video Object Detection	Shiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng	In this paper, we propose an end-to-end model called fully motion-aware network (MANet), which jointly calibrates the features of objects on both pixel-level and instance-level in a unified framework.
191	Learning to Forecast and Refine Residual Motion for Image-to-Video Generation	Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris Metaxas	We combine the benefits of both approaches and propose a two-stage generation framework where videos are generated from structures and then refined by temporal signals.
192	Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection	Jie Zhang, Yi Xu, Bingbing Ni, Zhenyu Duan	In this paper, we establish a multiple-task learning framework to segment lane areas and detect lane boundaries simultaneously.
193	Deterministic Consensus Maximization with Biconvex Programming	Zhipeng Cai, Tat-Jun Chin, Huu Le, David Suter	In this paper, we propose an efficient deterministic optimization algorithm for consensus maximization.
194	Lifting Layers: Analysis and Applications	Peter Ochs, Tim Meinhardt, Laura Leal-Taixe, Michael Moeller	In this paper we propose a novel non-linear transfer function, called lifting, which is motivated from a related technique in convex optimization.
195	Simultaneous Edge Alignment and Learning	Zhiding Yu, Weiyang Liu, Yang Zou, Chen Feng, Srikumar Ramalingam, B. V. K. Vijaya Kumar, Jan Kautz	In this paper, we show that label misalignment can cause considerably degraded edge learning quality, and address this issue by proposing a simultaneous edge alignment and learning framework.
196	Deep Feature Pyramid Reconfiguration for Object Detection	Tao Kong, Fuchun Sun, Chuanqi Tan, Huaping Liu, Wenbing Huang	In this paper, we begin by investigating current feature pyramids solutions, and then reformulate the feature pyramid construction as the feature reconfiguration process.
197	Unpaired Image Captioning by Language Pivoting	Jiuxiang Gu, Shafiq Joty, Jianfei Cai, Gang Wang	We present an approach to this unpaired image captioning problem by language pivoting.
198	Goal-Oriented Visual Question Generation via Intermediate Rewards	Junjie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton van den Hengel	Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal.
199	Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry	Yonggen Ling, Linchao Bao, Zequn Jie, Fengming Zhu, Ziyang Li, Shanmin Tang, Yongsheng Liu, Wei Liu, Tong Zhang	In this work, we propose a nonlinear optimization-based monocular visual inertial odometry (VIO) with varying camera-IMU time offset modeled as an unknown variable.
200	Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks	Minho Shim, Young Hwi Kim, Kyungmin Kim, Seon Joo Kim	To this end, we introduce a new large-scale baseball video dataset called the BBDB, which is produced semi-automatically by using play-by-play texts available online.
201	Receptive Field Block Net for Accurate and Fast Object Detection	Songtao Liu, Di Huang, andYunhong Wang	In this paper, we explore an alternative to build a fast and accurate detector by strengthening lightweight features using a hand-crafted mechanism.
202	DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model	Stephane Lathuiliere, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud	In this paper we address the problem of how to robustly train a ConvNet for regression, or deep robust regression.
203	Deep Bilinear Learning for RGB-D Action Recognition	Jian-Fang Hu, Wei-Shi Zheng, Jiahui Pan, Jianhuang Lai, Jianguo Zhang	In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition.
204	RelocNet: Continuous Metric Learning Relocalisation using Neural Nets	Vassileios Balntas, Shuda Li, Victor Prisacariu	We propose a method of learning suitable convolutional representations for camera pose retrieval based on nearest neighbour matching and continuous metric learning-based feature descriptors.
205	Generative Semantic Manipulation with Mask-Contrasting GAN	Xiaodan Liang, Hao Zhang, Liang Lin, Eric Xing	In this work, we focus on a more challenging semantic manipulation task, aiming at modifying the semantic meaning of an object while preserving its own characteristics (e.g. viewpoints and shapes), such as cow$ ightarrow$sheep, motor$ ightarrow$ bicycle, cat$ ightarrow$dog.
206	Interpolating Convolutional Neural Networks Using Batch Normalization	Gratianus Wesley Putra Data, Kirjon Ngu, David William Murray, Victor Adrian Prisacariu	Inspired by recent work on universal representations for neural networks, we propose a simple emulation of this mechanism by purposing batch normalization layers to discriminate visual classes, and formulating a way to combine them to solve new tasks.
207	SketchyScene: Richly-Annotated Scene Sketches	Changqing Zou, Qian Yu, Ruofei Du, Haoran Mo, Yi-Zhe Song, Tao Xiang, Chengying Gao, Baoquan Chen, Hao Zhang	We contribute the rst large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level.
208	An Adversarial Approach to Hard Triplet Generation	Yiru Zhao, Zhongming Jin, Guo-jun Qi, Hongtao Lu, Xian-sheng Hua	For this purpose, we propose an adversarial network for Hard Triplet Generation (HTG) to optimize the network ability in distinguishing similar examples of different categories as well as grouping varied examples of the same categories.
209	Toward Characteristic-Preserving Image-based Virtual Try-On Network	Bochao Wang, Huabin Zheng, Xiaodan Liang, Yimin Chen, Liang Lin, Meng Yang	In this work, we propose a new fully-learnable Characteristic-Preserving Virtual Try-On Network(CP-VTON) for addressing all real-world challenges in this task.
210	Estimating the Success of Unsupervised Image to Image Translation	Sagie Benaim, Tomer Galanti, Lior Wolf	We propose a novel bound for predicting the success of unsupervised cross domain mapping methods, which is motivated by the recently proposed simplicity hypothesis.
211	SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images	Benjamin Coors, Alexandru Paul Condurache, Andreas Geiger	In this work, we present SphereNet, a novel deep learning framework which encodes invariance against such distortions explicitly into convolutional neural networks.
212	Efficient Uncertainty Estimation for Semantic Segmentation in Videos	Po-Yu Huang, Wan-Ting Hsu, Chun-Yueh Chiu, Ting-Fan Wu, Min Sun	In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure.
213	Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval	Jiaxin Chen, Yi Fang	To address this problem, we propose a novel framework to learn a discriminative deep cross-modality adaptation model in this paper.
214	Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization	Guoliang Kang, Liang Zheng, Yan Yan, Yi Yang	In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN).
215	ICNet for Real-Time Semantic Segmentation on High-Resolution Images	Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia	We focus on the challenging task of real-time semantic segmentation in this paper.
216	Parallel Feature Pyramid Network for Object Detection	Seung-Wook Kim, Hyong-Keun Kook, Jee-Young Sun, Mun-Cheon Kang, Sung-Jea Ko	To overcome this limitation, we propose a CNN-based object detection architecture, referred to as a parallel feature pyramid (FP) network (PFPNet), where the FP is constructed by widening the network width instead of increasing the network depth.
217	MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network	Muhammed Kocabas, Salih Karagoz, Emre Akbas	In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method.
218	Deep Directional Statistics: Pose Estimation with Uncertainty Quantification	Sergey Prokudin, Peter Gehler , Sebastian Nowozin	In this paper, we propose a novel probabilistic deep learning model for the task of angular regression.
219	Person Search by Multi-Scale Matching	Xu Lan , Xiatian Zhu , Shaogang Gong	In this work, we address this multi-scale person search challenge by proposing a Cross-Level Semantic Alignment (CLSA) deep learning approach capable of learning more discriminative identity feature representations in a unified end-to-end model.
220	Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility	Benjamin Hepp, Debadeepta Dey, Sudipta N. Sinha, Ashish Kapoor, Neel Joshi, Otmar Hilliges	We propose to learn a better utility function that predicts the usefulness of future viewpoints.
221	Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking	Yingjie Yao, Xiaohe Wu, Lei Zhang, Shiguang Shan, Wangmeng Zuo	In this paper, we investigate the joint learning of deep representation and model adaptation, where an updater network is introduced for better tracking on future frame by taking current frame representation, tracking result, and last CF tracker as input.
222	TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection	Yunchao Wei, Zhiqiang Shen, Bowen Cheng, Honghui Shi, Jinjun Xiong, Jiashi Feng, Thomas Huang	This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C).
223	Hierarchy of Alternating Specialists for Scene Recognition	Hyo Jin Kim, Jan-Michael Frahm	We introduce a method for improving convolutional neural networks (CNNs) for scene classification.
224	Revisiting RCNN: On Awakening the Classification Power of Faster RCNN	Bowen Cheng, Yunchao Wei, Honghui Shi, Rogerio Feris, Jinjun Xiong, Thomas Huang	In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization.
225	A Hybrid Model for Identity Obfuscation by Face Replacement	Qianru Sun, Ayush Tewari, Weipeng Xu, Mario Fritz, Christian Theobalt, Bernt Schiele	We propose a new hybrid approach to obfuscate identities in photos by head replacement.
226	3D Scene Flow from 4D Light Field Gradients	Sizhuo Ma, Brandon M. Smith, Mohit Gupta	This paper presents novel techniques for recovering 3D dense scene flow, based on differential analysis of 4D light fields.
227	RIDI: Robust IMU Double Integration	Hang Yan, Qi Shan, Yasutaka Furukawa	This paper proposes a novel data-driven approach for inertial navigation, which learns to estimate trajectories of natural human motions just from an inertial measurement unit (IMU) in every smartphone.
228	Superpixel Sampling Networks	Varun Jampani, Deqing Sun, Ming-Yu Liu, Ming-Hsuan Yang, Jan Kautz	We develop a new differentiable model for superpixel sampling that leverages deep networks for learning superpixel segmentation.
229	Towards Robust Neural Networks via Random Self-ensemble	Xuanqing Liu, Minhao Cheng, Huan Zhang, Cho-Jui Hsieh	In this paper, we propose a new defense algorithm called Random Self-Ensemble (RSE) by combining two important concepts: randomness and ensemble.
230	The Sound of Pixels	Hang Zhao, Chuang Gan, Andrew Rouditchenko, Carl Vondrick, Josh McDermott, Antonio Torralba	We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos, learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel.
231	Adaptive Affinity Fields for Semantic Segmentation	Tsung-Wei Ke, Jyh-Jing Hwang, Ziwei Liu , Stella X. Yu	Instead of learning to enforce semantic labels on individual pixels, we propose to enforce affinity field patterns in individual pixel neighbourhoods, i.e., the semantic label patterns of whether neighbour pixels are in the same segment should match between the prediction and the ground-truth.
232	Joint Map and Symmetry Synchronization	Yifan Sun, Zhenxiao Liang, Xiangru Huang, Qixing Huang	In this paper, we study the problem of jointly optimizing self-symmetries and pair-wise maps among a collection of similar objects.
233	EC-Net: an Edge-aware Point set Consolidation Network	Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng	In this paper, we present the first deep learning based {em edge-aware} technique to facilitate the consolidation of point clouds.
234	ReenactGAN: Learning to Reenact Faces via Boundary Transfer	Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, Chen Change Loy	We present a novel learning-based framework for face reenactment.
235	Semi-Supervised Generative Adversarial Hashing for Image Retrieval	Guan’an Wang, Qinghao Hu, Jian Cheng, Zengguang Hou	In this paper, inspired by the idea of generative models and the minimax two-player game, we propose a novel semi-supervised generative adversarial hashing (SSGAH) approach.
236	Training Binary Weight Networks via Semi-Binary Decomposition	Qinghao Hu, Gang Li, Peisong Wang, Yifan Zhang, Jian Cheng	In this paper, we propose a novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix.
237	Part-Activated Deep Reinforcement Learning for Action Prediction	Lei Chen, Jiwen Lu, Zhanjie Song, Jie Zhou	In this paper, we propose a part-activated deep reinforcement learning (PA-DRL) for action prediction.
238	Learning to Anonymize Faces for Privacy Preserving Action Detection	Zhongzheng Ren, Yong Jae Lee, Michael S. Ryoo	In this paper, we propose a new principled approach for learning a video anonymizer.
239	Lifelong Learning via Progressive Distillation and Retrospection	Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, Dahua Lin	In this work, we propose a novel approach to lifelong learning, which tries to seek a better balance between preservation and adaptation via two techniques: Distillation and Retrospection.
240	Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor Segmentation	Xuan Chen, Jun Hao Liew, Wei Xiong, Chee-Kong Chui, Sim-Heng Ong	In this paper, we propose a novel end-to-end trainable network named FSENet to address the aforementioned issues.
241	Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition	Xiaohang Zhan , Ziwei Liu, Junjie Yan , Dahua Lin , Chen Change Loy	In this work, we show that unlabeled face data can be as effective as the labeled ones.
242	A Closed-form Solution to Photorealistic Image Stylization	Yijun Li, Ming-Yu Liu, Xueting Li, Ming-Hsuan Yang, Jan Kautz	In this paper, we propose a method to address these issues.
243	MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics	Xinchen Yan, Akash Rastogi, Ruben Villegas, Kalyan Sunkavalli, Eli Shechtman, Sunil Hadap, Ersin Yumer, Honglak Lee	We leverage this structure and present a novel Motion Transformation Variational Auto-Encoders (MT-VAE) for learning motion sequence generation.
244	3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation	Xiaoqing Ye, Jiamao Li, Hexiao Huang, Liang Du, Xiaolin Zhang	In this paper, a novel end-to-end approach for unstructured point cloud semantic segmentation is proposed to exploit the inherent contextual features.
245	Rethinking the Form of Latent States in Image Captioning	Bo Dai, Deming Ye, Dahua Lin	Existing captioning models usually represent latent states as vectors, taking this practice for granted.
246	Move Forward and Tell: A Progressive Generator of Video Descriptions	Yilei Xiong, Bo Dai, Dahua Lin	We present an efficient framework that can generate a coherent paragraph to describe a given video.
247	Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos	Mingze Xu, Chenyou Fan, Yuchen Wang, Michael S. Ryoo, David J. Crandall	In this paper, we wish to solve two specific problems: (1) given two or more synchronized third-person videos of a scene, produce a pixel-level segmentation of each visible person and identify corresponding people across different views (i.e., determine who in camera A corresponds with whom in camera B), and (2) given one or more synchronized third-person videos as well as a first-person video taken by a mobile or wearable camera, segment and identify the camera wearer in the third-person videos.
248	Transductive Semi-Supervised Deep Learning using Min-Max Features	Weiwei Shi, Yihong Gong, Chris Ding, Zhiheng MaXiaoyu Tao, Nanning Zheng	In this paper, we propose Transductive Semi-Supervised Deep Learning (TSSDL) method that is effective for training Deep Convolutional Neural Network (DCNN) models.
249	SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection	Yonghyun Kim, Bong-Nam Kang, Daijin Kim	We evaluate our method on VOC PASCAL and MS COCO dataset.
250	Visual Tracking via Spatially Aligned Correlation Filters Network	Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, Steve Maybank	Visual Tracking via Spatially Aligned Correlation Filters Network
251	Predicting Future Instance Segmentation by Forecasting Convolutional Features	Pauline Luc, Camille Couprie, Yann LeCun, Jakob Verbeek	In this paper we consider the more challenging problem of future instance segmentation, which additionally segments out individual objects.
252	MVSNet: Depth Inference for Unstructured Multi-view Stereo	Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan	We present an end-to-end deep learning architecture for depth map inference from multi-view images.
253	Learning Monocular Depth by Distilling Cross-domain Stereo Networks	Xiaoyang Guo, Hongsheng Li, Shuai Yi, Jimmy Ren, Xiaogang Wang	In this paper, we propose to use the stereo matching network as a proxy to learn depth from synthetic data and use predicted stereo disparity maps for supervising the monocular depth estimation network.
254	Person Re-identification with Deep Similarity-Guided Graph Neural Network	Yantao Shen, Hongsheng Li, Shuai Yi, Dapeng Chen, Xiaogang Wang	In this paper, we propose a novel deep learning framework, named Similarity-Guided Graph Neural Network (SGGNN) to overcome such limitations.
255	Learning and Matching Multi-View Descriptors for Registration of Point Clouds	Lei Zhou, Siyu Zhu, Zixin Luo, Tianwei Shen, Runze Zhang, Mingmin Zhen, Tian Fang, Long Quan	We have demonstrated the boost of our approaches to registration on the public scanning and multi-view stereo datasets.
256	Flow-Grounded Spatial-Temporal Video Prediction from Still Images	Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang	In this work, we study the problem of generating consecutive multiple future frames by observing one single still image only.
257	The Contextual Loss for Image Transformation with Non-Aligned Data	Roey Mechrez, Itamar Talmi, Lihi Zelnik-Manor	We present an alternative loss function that does not require alignment, thus providing an effective and simple solution for a new space of problems.
258	Online Dictionary Learning for Approximate Archetypal Analysis	Jieru Mei, Chunyu Wang, Wenjun Zeng	We propose a variant of archetypal analysis which scales gracefully to large datasets.
259	Video Object Segmentation by Learning Location-Sensitive Embeddings	Hai Ci, Chunyu Wang, Yizhou Wang	To deal with appearance changes, for a test video, we propose a robust model adaptation method which pre-scans the whole video, generates pseudo foreground/background labels and retrains the model based on the labels.
260	Hashing with Binary Matrix Pursuit	Fatih Cakir, Kun He, Stan Sclaroff	We propose theoretical and empirical improvements for two-stage hashing methods.
261	Learning to Capture Light Fields through a Coded Aperture Camera	Yasutaka Inagaki, Yuto Kobayashi, Keita Takahashi, Toshiaki Fujii, Hajime Nagahara	We propose a learning-based framework for acquiring a light field through a coded aperture camera.
262	Learning to Reconstruct High-quality 3D Shapes with Cascaded Fully Convolutional Networks	Yan-Pei Cao, Zheng-Ning Liu, Zheng-Fei Kuang, Leif Kobbelt, Shi-Min Hu	We present a data-driven approach to reconstructing high-resolution and detailed volumetric representations of 3D shapes.
263	X2Face: A network for controlling face generation using images, audio, and pose codes	Olivia Wiles, A. Sophia Koepke, Andrew Zisserman	The objective of this paper is a neural network model that controls the pose and expression of a given face, using another face or modality (e.g. audio).
264	End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners	Simon Hecker, Dengxin Dai, Luc Van Gool	We investigate the problem in a more realistic setting, which consists of a surround-view camera system with eight cameras, a route planner, and a CAN bus reader. With such a sensor setup we collect a new driving dataset, covering diverse driving scenarios and varying weather/illumination conditions.
265	Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding	Christos Sakaridis, Dengxin Dai, Simon Hecker, Luc Van Gool	In this paper, we propose a novel method, named Curriculum Model Adaptation (CMAda), which gradually adapts a semantic segmentation model from light synthetic fog to dense real fog in multiple steps, using both synthetic and real foggy data.
266	DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures	Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun	We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., inference time and memory usage) and device-agnostic (e.g., accuracy and model size) objectives.
267	Revisiting Autofocus for Smartphone Cameras	Abdullah Abuolaim, Abhijith Punnappurath, Michael S. Brown	The work in this paper aims to revisit AF for smartphones within the context of temporal image data.
268	Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence	Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan, Philip H. S. Torr	One of the main objectives of this work is to fill these gaps so as to provide a common ground for better understanding of IL.
269	A Dataset of Flash and Ambient Illumination Pairs from the Crowd	Yagiz Aksoy, Changil Kim, Petr Kellnhofer, Sylvain Paris, Mohamed Elgharib, Marc Pollefeys, Wojciech Matusik	We present a dataset of thousands of ambient and flash illumination pairs to enable studying flash photography and other applications that can benefit from having separate illuminations. Different than the typical use of crowdsourcing in generating computer vision datasets, we make use of the crowd to directly take the photographs that make up our dataset.
270	Deep Burst Denoising	Clement Godard, Kevin Matzen, Matt Uyttendaele	In this paper, we use the burst-capture strategy and implement the intelligent integration via a recurrent fully convolutional deep neural net (CNN).
271	MaskConnect: Connectivity Learning by Gradient Descent	Karim Ahmed, Lorenzo Torresani	In this work we remove these predefined choices and propose an algorithm to learn the connections between modules in the network.
272	ISNN: Impact Sound Neural Network for Audio-Visual Object Classification	Auston Sterling, Justin Wilson, Sam Lowe, Ming C. Lin	We evaluate our method on multiple datasets of both recorded and synthesized sounds.
273	Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets	Xiaofeng Liu, B.V.K Vijaya Kumar, Chao Yang, Qingming Tang, Jane You	Specifically, we propose a dependency-aware attention control (DAC) network, which resorts to actor-critic reinforcement learning for sequential attention decision of each image embedding to fully exploit the rich correlation cues among the unordered images.
274	StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction	Sameh Khamis, Sean Fanello, Christoph Rhemann, Adarsh Kowdle, Julien Valentin, Shahram Izadi	A key insight of this paper is that the network achieves a sub-pixel matching precision than is a magnitude higher than those of traditional stereo matching approaches.
275	Compositing-aware Image Search	Hengshuang Zhao, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Brian Price, Jiaya Jia	We present a new image search technique that, given a background image, returns compatible foreground objects for image compositing tasks. We collect an evaluation set consisting of eight object categories commonly used in compositing tasks, on which we demonstrate that our approach significantly outperforms other search techniques.
276	Online Multi-Object Tracking with Dual Matching Attention Networks	Ji Zhu, Hua Yang, Nian Liu, Minyoung Kim, Wenjun Zhang, Ming-Hsuan Yang	In this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent interactions between targets.
277	Improving Sequential Determinantal Point Processes for Supervised Video Summarization	Aidean Sharghi , Ali Borji, Chengtao Li , Tianbao Yang , Boqing Gong	In terms of learning, we propose a large-margin algorithm to address the exposure bias problem in SeqDPP.
278	Online Detection of Action Start in Untrimmed, Streaming Videos	Zheng Shou, Junting Pan, Jonathan Chan, Kazuyuki Miyazawa, Hassan Mansour, Anthony Vetro, Xavier Giro-i-Nieto, Shih-Fu Chang	We propose three novel methods to specifically address the challenges in training ODAS models: (1) hard negative samples generation based on Generative Adversarial Network (GAN) to distinguish ambiguous background, (2) explicitly modeling the temporal consistency between data around action start and data succeeding action start, and (3) adaptive sampling strategy to handle the scarcity of training data.
279	Volumetric performance capture from minimal camera viewpoints	Andrew Gilbert, Marco Volino, John Collomosse, Adrian Hilton	We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set of camera views.
280	Coreset-Based Neural Network Compression	Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja	We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters.
281	A Framework for Evaluating 6-DOF Object Trackers	Mathieu Garon, Denis Laurendeau, Jean-Francois Lalonde	We present a challenging and realistic novel dataset for evaluating 6-DOF object tracking algorithms. Using a data acquisition pipeline based on a commercial motion capture system for acquiring accurate ground truth poses of real objects with respect to a Kinect V2 camera, we build a dataset which contains a total of 297 calibrated sequences.
282	Learning to Separate Object Sounds by Watching Unlabeled Video	Ruohan Gao, Rogerio Feris, Kristen Grauman	We propose to learn audio-visual object models from unlabeled video, then exploit the visual context to perform audio source separation in novel videos.
283	Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency	Eunji Chong, Nataniel Ruiz, Yongxin Wang, Yun Zhang, Agata Rozga, James M. Rehg	This paper addresses the challenging problem of estimating the general visual attention of people in images.
284	Neural Graph Matching Networks for Fewshot 3D Action Recognition	Michelle Guo, Edward Chou, De-An Huang, Shuran Song, Serena Yeung, Li Fei-Fei	We propose Neural Graph Matching (NGM) Networks, a novel framework that can learn to recognize a previous unseen 3D action class with only a few examples.
285	Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos	Bingbin Liu, Serena Yeung, Edward Chou, De-An Huang, Li Fei-Fei, Juan Carlos Niebles	In this work, we introduce an approach for explicitly and dynamically reasoning about compositional natural language descriptions of activity in videos.
286	Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval	Xi Zhang, Hanjiang Lai , Jiashi Feng	To further address this problem, we propose an adversarial hashing network with an attention mechanism to enhance the measurement of content similarities by selectively focusing on the informative parts of multi-modal data.
287	3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration	Zi Jian Yew, Gim Hee Lee	In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision. We create training and benchmark outdoor Lidar datasets, and our experiments on these datasets show that our 3DFeat-Net outperforms existing handcrafted and learned 3D features.
288	Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers	Eunbyung Park, Alexander C. Berg	Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking.
289	Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with An Ordinary Camera	Ko Nishino, Art Subpa-asa, Yuta Asano, Mihoko Shimano, Imari Sato	We introduce a novel imaging method that enables the decomposition of the appearance of a fronto-parallel real-world surface into images of light with bounded path lengths, i.e., transient subsurface light transport.
290	Graph R-CNN for Scene Graph Generation	Jianwei Yang, Jiasen Lu, Stefan Lee, Dhruv Batra, Devi Parikh	We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images.
291	Deep Domain Generalization via Conditional Invariant Adversarial Networks	Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu, Tongliang Liu, Kun Zhang, Dacheng Tao	To address the above two drawbacks, we propose an end-to-end conditional invariant deep domain generalization approach by leveraging deep neural networks for domain-invariant representation learning.
292	Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks	Siqi Yang, Arnold Wiliem, Shaokang Chen, Brian C. Lovell	In this paper, we call this problem the Instance Perturbation Interference (IPI) problem.
293	Pose-Normalized Image Generation for Person Re-identification	Xuelin Qian, Yanwei Fu, Tao Xiang, Wenxuan Wang, Jie Qiu, Yang Wu, Yu-Gang Jiang, Xiangyang Xue	In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on the pose.
294	Videos as Space-Time Region Graphs	Xiaolong Wang, Abhinav Gupta	In this paper, we propose to represent videos as space-time region graphs which capture these two important cues.
295	Learning 3D Human Pose from Structure and Motion	Rishabh Dabral, Anurag Mundhada, Uday Kusupati, Safeer Afaque, Abhishek Sharma, Arjun Jain	We propose two anatomically inspired loss functions and use them with a weakly-supervised learning framework to jointly learn from large-scale in-the-wild 2D and indoor/synthetic 3D data.
296	Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment	Zhiwen Shao, Zhilei Liu, Jianfei Cai, Lizhuang Ma	In this paper, we propose a novel end-to-end deep learning framework for joint AU detection and face alignment, which has not been explored before.
297	HiDDeN: Hiding Data with Deep Networks	Jiren Zhu, Russell Kaplan, Justin Johnson, Li Fei-Fei	Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples.
298	Deep Cross-Modal Projection Learning for Image-Text Matching	Ying Zhang, Huchuan Lu	In this paper, we propose a cross-modal projection matching (CMPM) loss and a cross-modal projection classification (CMPC) loss for learning discriminative image-text embeddings.
299	Large Scale Urban Scene Modeling from MVS Meshes	Lingjie Zhu, Shuhan Shen, Xiang Gao, Zhanyi Hu	In this paper we present an effcient modeling framework for large scale urban scenes.
300	Dual-Agent Deep Reinforcement Learning for Deformable Face Tracking	Minghao Guo, Jiwen Lu, Jie Zhou	In this paper, we propose a dual-agent deep reinforcement learning (DADRL) method for deformable face tracking, which generates bounding boxes and detects facial landmarks interactively from face videos.
301	Unified Perceptual Parsing for Scene Understanding	Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun	In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image.
302	Multimodal Dual Attention Memory for Video Story Question Answering	Kyung-Min Kim, Seong-Ho Choi, Jin-Hwa Kim, Byoung-Tak Zhang	We propose a video story question-answering (QA) architecture, Multimodal Dual Attention Memory (MDAM).
303	Deep Reinforcement Learning with Iterative Shift for Visual Tracking	Liangliang Ren, Xin Yuan, Jiwen Lu, Ming Yang, Jie Zhou	In this paper, we propose a deep reinforcement learning with iterative shift (DRL-IS) method for single object tracking, where an actor-critic network is introduced to predict the iterative shifts of object bounding boxes, and evaluate the shifts to take actions on whether to update object models or re-initialize tracking.
304	Collaborative Deep Reinforcement Learning for Multi-Object Tracking	Liangliang Ren, Jiwen Lu, Zifeng Wang, Qi Tian, Jie Zhou	In this paper, we propose a collaborative deep reinforcement learning (C-DRL) method for multi-object tracking.
305	Deep Variational Metric Learning	Xudong Lin, Yueqi Duan, Qiyuan Dong, Jiwen Lu, Jie Zhou	In this paper, we propose a deep variational metric learning (DVML) framework to explicitly model the intra-class variance and disentangle the intra-class invariance, namely, the class centers.
306	A Joint Sequence Fusion Model for Video Question Answering and Retrieval	Youngjae Yu , Jongseok Kim , Gunhee Kim	We present an approach named JSFusion (Joint Sequence Fusion) that can measure semantic similarity between any pairs of multimodal sequence data (e.g. a video sequence and a language sentence).
307	Deep Pictorial Gaze Estimation	Seonwook Park, Adrian Spurr, Otmar Hilliges	In this paper, we introduce a novel deep neural network architecture specifically designed for the task of gaze estimation from single eye input.
308	PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene Reconstruction	Wei Dong, Qiuyuan Wang, Xin Wang, Hongbin Zha	We propose a novel 3D spatial representation for data fusion and scene reconstruction.
309	Multi-Scale Context Intertwining for Semantic Segmentation	Di Lin, Yuanfeng Ji, Dani Lischinski, Daniel Cohen-Or, Hui Huang	In this work, we propose a novel scheme for aggregating features from different scales, which we refer to as Multi-Scale Context Intertwining (MSCI).
310	Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching	Johannes L. Schonberger, Sudipta N. Sinha, Marc Pollefeys	We propose replacing this aggregation scheme with a new learning-based method that fuses disparity proposals estimated using scanline optimization.
311	Saliency Detection in 360° Videos	Ziheng Zhang, Yanyu Xu, Jingyi Yu, Shenghua Gao	This paper presents a novel spherical convolutional neural network based scheme for saliency detection for 360° videos. To validate our approach, we construct a large-scale 360° videos saliency detection benchmark that consists of 104 360° videos viewed by 20+ human subjects.
312	Scaling Egocentric Vision: The EPIC-KITCHENS Dataset	Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray	In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments.
313	AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation	Sheng-Wei Huang, Che-Tsung Lin, Shu-Ping Chen, Yen-Yi Wu, Po-Hao Hsu, Shang-Hong Lai	Despite recent GAN (Generative Adversarial Network) based methods have shown compelling visual results, they are prone to fail at preserving image-objects and maintaining translation consistency when faced with large and complex domain shifts, which reduces their practicality on tasks such as generating large-scale training data for different domains.
314	Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length	Thomas Probst, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool	On its basis we propose a method to simultaneously recover the focal length and the non-rigid shapes.
315	Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries	Edgar Margffoy-Tuay, Juan C. Perez, Emilio Botero, Pablo Arbelaez	We propose a novel method that integrates these two insights in order to fully exploit the recursive nature of language.
316	Graininess-Aware Deep Feature Learning for Pedestrian Detection	Chunze Lin, Jiwen Lu, Gang Wang, Jie Zhou	In this paper, we propose a graininess-aware deep feature learning method for pedestrian detection.
317	Acquisition of Localization Confidence for Accurate Object Detection	Borui Jiang, Ruixuan Luo, Jiayuan Mao, Tete Xiao, Yuning Jiang	In the paper we propose IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth.
318	Learning Shape Priors for Single-View 3D Completion and Reconstruction	Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T. Freeman, Joshua B. Tenenbaum	In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors.
319	R2P2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting	Nicholas Rhinehart, Kris M. Kitani, Paul Vernaza	We propose a method to forecast a vehicle’s ego-motion as a distribution over spatiotemporal paths, conditioned on features (e.g., from LIDAR and images) embedded in an overhead map.
320	Synthetically Supervised Feature Learning for Scene Text Recognition	Yang Liu, Zhaowen Wang, Hailin Jin, Ian Wassell	We propose to leverage the parameters that lead to the output images to improve image feature learning.
321	Localization Recall Precision (LRP): A New Performance Metric for Object Detection	Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan	In this paper, we propose “Localization Recall Precision (LRP) Error”, a new metric specifically designed for object detection.
322	Second-order Democratic Aggregation	Tsung-Yu Lin, Subhransu Maji, Piotr Koniusz	In this paper we study a class of orderless aggregation functions designed to minimize emph{interference} or equalize emph{contributions} in the context of second-order features and show that they can be computed just as efficiently as their first-order counterparts and have favorable properties over aggregation by summation.
323	Lip Movements Generation at a Glance	Lele Chen, Zhiheng Li, Ross K Maddox, Zhiyao Duan, Chenliang Xu	In this paper, we consider a task of such: given an arbitrary audio speech and one lip image of arbitrary target identity, generate synthesized lip movements of the target identity saying the speech.
324	Probabilistic Video Generation using Holistic Attribute Control	Jiawei He, Andreas Lehrmann, Joseph Marino, Greg Mori, Leonid Sigal	Based on this intuition, we propose a generative framework for video generation and future prediction.
325	AGIL: Learning Attention from Human for Visuomotor Tasks	Ruohan Zhang, Zhuode Liu, Luxin Zhang, Jake A. Whritner, Karl S. Muller, Mary M. Hayhoe, Dana H. Ballard	With this motivation, we propose the AGIL (Attention Guided Imitation Learning) framework.
326	Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd	Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li	In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy in the crowd.
327	Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery	Greire Payen de La Garanderie, Amir Atapour Abarghouei, Toby P. Breckon	We present an approach to adapt contemporary deep network architectures developed on conventional rectilinear imagery to work on equirectangular 360° panoramic imagery.
328	Seeing Tree Structure from Vibration	Tianfan Xue, Jiajun Wu, Zhoutong Zhang, Chengkai Zhang, Joshua B. Tenenbaum, William T. Freeman	We propose to tackle this problem through spectrum analysis of motion signals, because vibrations of disconnected branches, though visually similar, often have distinctive natural frequencies.
329	Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation	Zhaoyang Lv, Kihwan Kim, Alejandro Troccoli, Deqing Sun, James M. Rehg, Jan Kautz	Compared to other state-of-the-art 3D scene flow estimation methods, in this paper we propose to emph{learn} the rigidity of a scene in a supervised manner from a large collection of dynamic scene data, and directly infer a rigidity mask from two sequential images with depths. For training and testing the rigidity network, we also provide a new semi-synthetic dynamic scene dataset (synthetic foreground objects with a real background) and an evaluation split that accounts for the percentage of observed non-rigid pixels.
330	HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration	B. Eckart, K. Kim, J. Kautz	In this paper, we present a new registration algorithm that is able to achieve state-of-the-art speed and accuracy through its use of a Hierarchical Gaussian Mixture representation.
331	Deep Imbalanced Attribute Classification using Visual Attention Aggregation	Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris	With that in mind, we propose an effective method that extracts and aggregates visual attention masks at different scales.
332	Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T Tracking	Chenglong Li, Chengli Zhu, Yan Huang, Jin Tang, Liang Wang	To address this problem, this paper presents a novel approach to suppress background effects for RGB-T tracking.
333	Shift-Net: Image Inpainting via Deep Feature Rearrangement	Zhaoyi Yan, Xiaoming Li, Mu Li, Wangmeng Zuo, Shiguang Shan	In this paper, we introduce a special shift-connection layer to the U-Net architecture, namely Shift-Net, for filling in missing regions of any shape with sharp structures and fine-detailed textures.
334	Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation	Tao Song, Leiyu Sun, Di Xie, Haiming Sun, Shiliang Pu	Motivated by this, we propose a novel method integrated with somatic topological line localization (TLL) and temporal feature aggregation for detecting multi-scale pedestrians, which works particularly well with small-scale pedestrians that are relatively far from the camera.
335	Sub-GAN: An Unsupervised Generative Model via Subspaces	Jie Liang, Jufeng Yang, Hsin-Ying Lee, Kai Wang, Ming-Hsuan Yang	In this paper, we present a subspace-based generative adversarial network (Sub-GAN) which simultaneously disentangles multiple latent subspaces and generates diverse samples correspondingly.
336	VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions	Qing Li, Qingyi Tao, Shafiq Joty, Jianfei Cai, Jiebo Luo	To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-task learning architecture.
337	Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation	Xinge Zhu, Hui Zhou, Ceyuan Yang, Jianping Shi, Dahua Lin	To this end, we propose a novel loss function, i.e., Conservative Loss, which penalizes the extreme good and bad cases while encouraging the moderate examples.
338	Interactive Boundary Prediction for Object Selection	Hoang Le, Long Mai, Brian Price, Scott Cohen, Hailin Jin, Feng Liu	In this paper, we introduce an interaction-aware method for boundary-based image segmentation.
339	Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection	Hongmei Song, Wenguan Wang, Sanyuan Zhao, Jianbing Shen, Kin-Man Lam	This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM).
340	CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving	Xiaodan Liang, Tairui Wang, Luona Yang, Eric Xing	We present a general and principled Controllable Imitative Reinforcement Learning (CIRL) approach which successfully makes the driving agent achieve higher success rates based on only vision inputs in a high-fidelity car simulator.
341	The Devil of Face Recognition is in the Noise	Fei Wang, Liren Chen, Cheng Li, Shiyao Huang, Yanjie Chen, Chen Qian, Chen Change Loy	4) We investigate ways to improve data cleanliness, including a comprehensive user study on the influence of data labeling strategies to annotation accuracy. We make the following contributions: 1) We contribute cleaned subsets of popular face databases, i.e., MegaFace and MS-Celeb-1M datasets, and build a new large-scale noise-controlled IMDb-Face dataset.
342	Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion using Conditional Variational Autoencoders	Panna Felsen, Patrick Lucey, Sujoy Ganguly	In this paper, we present a technique using conditional variational autoencoder which learns a model that “personalizes” prediction to individual agent behavior within a group representation.
343	Bi-Real Net: Enhancing the Performance of 1-bit CNNs with Improved Representational Capability and Advanced Training Algorithm	Zechun Liu, Baoyuan Wu, Wenhan Luo, Xin Yang, Wei Liu, Kwang-Ting Cheng	In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary.
344	X-ray Computed Tomography Through Scatter	Adam Geva, Yoav Y. Schechner, Yonatan Chernyak, Rajiv Gupta	Treating these scattered photons as a source of information, we solve an inverse problem based on a 3D radiative transfer model that includes both elastic (Rayleigh) and inelastic (Compton) scattering.
345	Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency	Vincent Leroy, Jean-Sebastien Franco, Edmond Boyer	We consider in this paper the problem of 3D shape reconstruction from multi-view RGB images.
346	Unsupervised CNN-based Co-Saliency Detection with Graphical Optimization	Kuang-Jui Hsu, Chung-Chi Tsai, Yen-Yu Lin, Xiaoning Qian, Yung-Yu Chuang	In this paper, we address co-saliency detection in a set of images jointly covering objects of a specific class by an unsupervised convolutional neural network (CNN).
347	Unsupervised Person Re-identification by Deep Learning Tracklet Association	Minxian Li, Xiatian Zhu, Shaogang Gong	In this work, we address this problem by proposing an unsupervised re-id deep learning approach capable of incrementally discovering and exploiting the underlying re-id discriminative information from automatically generated person tracklet data from videos in an end-to-end deep model optimisation.
348	Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal	Jie Yang, Dong Gong, Lingqiao Liu, Qinfeng Shi	We propose a cascade deep neural network, which estimates both the background image and the reflection.
349	Learning Data Terms for Non-blind Deblurring	Jiangxin Dong, Jinshan Pan, Deqing Sun, Zhixun Su, Ming-Hsuan Yang	We propose a simple and effective discriminative framework to learn data terms that can adaptively handle blurred images in the presence of severe noise and outliers.
350	Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation	Xuecheng Nie, Jiashi Feng, Shuicheng Yan	This paper presents a novel Mutual Learning to Adapt model (MuLA) for joint human parsing and pose estimation.
351	Statistically-motivated Second-order Pooling	Kaicheng Yu, Mathieu Salzmann	Here, by contrast, we introduce a statistically-motivated framework that projects the second-order descriptor into a compact vector while improving the representational power.
352	Video Re-localization	Yang Feng, Lin Ma, Wei Liu, Tong Zhang, Jiebo Luo	Subsequently, we propose an innovative cross gated bilinear matching model such that every time-step in the reference video is matched against the attentively weighted query video.
353	Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition	Yitong Wang, Dihong Gong, Zheng Zhou, Xing Ji, Hao Wang, Zhifeng Li, Wei Liu, Tong Zhang	To reduce the intra-class discrepancy caused by aging, in this paper we propose a novel approach (namely, Orthogonal Embedding CNNs, or OE-CNNs) to learn the age-invariant deep face features. Besides, for complementing the existing cross-age datasets and advancing the research in this field, we construct a brand-new large-scale Cross-Age Face dataset (CAF).
354	Long-term Tracking in the Wild: a Benchmark	Jack Valmadre, Luca Bertinetto, Joao F. Henriques, Ran Tao, Andrea Vedaldi, Arnold W.M. Smeulders, Philip H.S. Torr, Efstratios Gavves	We introduce the OxUvA dataset and benchmark for evaluating single-object tracking algorithms.
355	Affinity Derivation and Graph Merge for Instance Segmentation	Yiding Liu, Siyu Yang, Bin Li, Wengang Zhou, Jizheng Xu, Houqiang Li, Yan Lu	We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance.
356	Deep Model-Based 6D Pose Refinement in RGB	Fabian Manhardt, Wadim Kehl, Nassir Navab, Federico Tombari	We present a novel approach for model-based 6D pose refinement in color data.
357	Zero-Shot Deep Domain Adaptation	Kuan-Chuan Peng, Ziyan Wu, Jan Ernst	To tackle this issue, we propose zero-shot deep domain adaptation (ZDDA), which uses privileged information from task-irrelevant dual-domain pairs.
358	Comparator Networks	Weidi Xie, Li Shen, Andrew Zisserman	The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not.
359	Deep Regionlets for Object Detection	Hongyu Xu, Xutao Lv, Xiaoyu Wang, Zhou Ren, Navaneeth Bodla, Rama Chellappa	In this paper, we propose a novel object detection framework named “Deep Regionlets” by establishing a bridge between deep neural networks and conventional detection schema for accurate generic object detection.
360	DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation	Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gokhan Uzunbas, Tom Goldstein, Ser Nam Lim, Larry S. Davis	We present Dual Channel-wise Alignment Networks (DCAN), a simple yet effective approach to reduce domain shift at both pixel-level and feature-level.
361	Generating 3D Faces using Convolutional Mesh Autoencoders	Anurag Ranjan, Timo Bolkart, Soubhik Sanyal, Michael J. Black	To address this, we introduce a versatile model that learns a non-linear representation of a face using spectral convolutions on a mesh surface.
362	ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking	Oliver Groth, Fabian B. Fuchs, Ingmar Posner, Andrea Vedaldi	In this paper we investigate the passive acquisition of an intuitive understanding of physical principles as well as the active utilisation of this intuition in the context of generalised object stacking.
363	Physical Primitive Decomposition	Zhijian Liu, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu	In this paper, we study physical primitive decomposition—understanding an object through its components, each with physical and geometric attributes.
364	Inner Space Preserving Generative Pose Machine	Shuangjun Liu, Sarah Ostadabbas	In this paper, we introduce an image “inner space” preserving model that assigns an interpretable low-dimensional pose descriptor (LDPD) to an articulated figure in the image.
365	Perturbation Robust Representations of Topological Persistence Diagrams	Anirudh Som, Kowshik Thopalli, Karthikeyan Natesan Ramamurthy, Vinay Venkataraman, Ankita Shukla, Pavan Turaga	In this paper we present theoretically well-grounded approaches to develop novel perturbation robust topological representations, with the long-term view of making them amenable to fusion with contemporary learning architectures.
366	Hierarchical Relational Networks for Group Activity Recognition and Retrieval	Mostafa S. Ibrahim, Greg Mori	We present a Hierarchical Relational Network that computes relational representations of people, given graph structures describing potential interactions.
367	Attention-based Ensemble for Deep Metric Learning	Wonsik Kim, Bhavya Goyal, Kunal Chawla, Jungmin Lee, Keunjoo Kwon	To this end, we propose an attention-based ensemble, which uses multiple attention masks, so that each learner can attend to different parts of the object.
368	Neural Procedural Reconstruction for Residential Buildings	Huayi Zeng, Jiaye Wu, Yasutaka Furukawa	This paper proposes a novel 3D reconstruction approach, dubbed Neural Procedural Reconstruction (NPR), which trains deep neural networks to procedurally apply shape grammar rules and reconstruct CAD-quality models from 3D points.
369	PyramidBox: A Context-assisted Single Shot Face Detector	Xu Tang, Daniel K. Du, Zeqiang He, Jingtuo Liu	This paper proposes a novel context-assisted single shot face detector, named emph{PyramidBox} to handle the hard face detection problem.
370	Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition	Yifei Huang, Minjie Cai, Zhenqiang Li, Yoichi Sato	We present a new computational model for gaze prediction in egocentric videos by exploring patterns in temporal shift of gaze fixations (attention transition) that are dependent on egocentric manipulation tasks.
371	Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes	Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai	In this paper, we investigate the problem of scene text spotting, which aims at simultaneous text detection and recognition in natural images.
372	Broadcasting Convolutional Network for Visual Relational Reasoning	Simyung Chang, John Yang, SeongUk Park, Nojun Kwak	In this paper, we propose the Broadcasting Convolutional Network (BCN) that extracts key object features from the global field of an entire input image and recognizes their relationship with local features.
373	Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning	Uta Buchler, Biagio Brattoli, Bjorn Ommer	Based on deep reinforcement learning we propose a sampling policy that adapts to the state of the network, which is being trained.
374	View-graph Selection Framework for SfM	Rajvi Shah, Visesh Chari, P J Narayanan	To model selection costs for this task, we introduce new disambiguation priors based on local geometry.
375	DFT-based Transformation Invariant Pooling Layer for Visual Classification	Jongbin Ryu, Ming-Hsuan Yang, Jongwoo Lim	We propose a novel discrete Fourier transform-based pooling layer for convolutional neural networks.
376	Learning Compression from Limited Unlabeled Data	Xiangyu He, Jian Cheng	In this paper, we reveal that re-normalization is the practical and effective way to alleviate the above limitations.
377	Bayesian Semantic Instance Segmentation in Open Set World	Trung Pham, Vijay Kumar B. G., Thanh-Toan Do, Gustavo Carneiro, Ian Reid	In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes.
378	BOP: Benchmark for 6D Object Pose Estimation	Tomas Hodan, Frank Michel, Eric Brachmann, Wadim Kehl, Anders GlentBuch, Dirk Kraft, Bertram Drost, Joel Vidal, Stephan Ihrke, Xenophon Zabulis, Caner Sahin, Fabian Manhardt, Federico Tombari, Tae-Kyun Kim, Jiri Matas, Carsten Rother	We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image.
379	3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints	Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, Rainer Stiefelhagen	We present a framework to reconstruct three-dimensional vehicle trajectories using monocular video data. Due to the lack of suitable benchmark datasets we present a new dataset to evaluate the quality of reconstructed three-dimensional vehicle trajectories.
380	Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric Regression	Yihua Cheng, Feng Lu, Xucong Zhang	In this paper, we propose the Asymmetric Regression-Evaluation Network (ARE-Net), and try to improve the gaze estimation performance to its full extent.
381	Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation	Chao Wang, Haiyong Zheng, Zhibin Yu, Ziqiang Zheng, Zhaorui Gu, Bing Zheng	In this paper, we present Discriminative Region Proposal Adversarial Networks (DRPAN) for high-quality image-to-image translation.
382	SegStereo: Exploiting Semantic Information for Disparity Estimation	Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, Jiaya Jia	In this paper, we suggest that appropriate incorporation of semantic cues can greatly rectify prediction in commonly-used disparity estimation frameworks.
383	ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design	Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun	Taking these factors into account, this work proposes practical guidelines for efficient network de- sign.
384	Deep Attention Neural Tensor Network for Visual Question Answering	Yalong Bai, Jianlong Fu, Tiejun Zhao, Tao Mei	In this paper, we propose a novel deep attention neural tensor network (DA-NTN) for visual question answering, which can discover the joint correlations over images, questions and answers with tensor-based representations.
385	Pairwise Body-Part Attention for Recognizing Human-Object Interactions	Hao-Shu Fang, Jinkun Cao, Yu-Wing Tai, Cewu Lu	In this paper, we argue that different body parts should be paid with different attention in HOI recognition, and the correlations between different body parts should be further considered.
386	Deep Clustering for Unsupervised Learning of Visual Features	Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze	In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features.
387	Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features	Xu Yang, Hanwang Zhang, Jianfei Cai	To alleviate the bias, we propose a novel Shuffle-Then-Assemble pre-training strategy.
388	Learning to Look around Objects for Top-View Representations of Outdoor Scenes	Samuel Schulter, Menghua Zhai, Nathan Jacobs, Manmohan Chandraker	We propose a convolutional neural network that learns to predict occluded portions of the scene layout by looking around foreground objects like cars or pedestrians.
389	Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow	Eddy Ilg, Ozgun Cicek, Silvio Galesso, Aaron Klein, Osama Makansi, Frank Hutter, Thomas Brox	In this paper, we make such networks estimate their local uncertainty about the correctness of their prediction, which is vital information when building decisions on top of the estimations.
390	Normalized Blind Deconvolution	Meiguang Jin, Stefan Roth, Paolo Favaro	In this paper we address this issue by looking at a much less studied aspect: the relative scale ambiguity between the sharp image and the blur.
391	Selfie Video Stabilization	Jiyang Yu, Ravi Ramamoorthi	We propose a novel algorithm for stabilizing selfie videos.
392	CubeNet: Equivariance to 3D Rotation and Translation	Daniel Worrall, Gabriel Brostow	We introduce a Group Convolutional Neural Network with linear equivariance to translations and right angle rotations in three dimensions.
393	Improving Generalization via Scalable Neighborhood Component Analysis	Zhirong Wu, Alexei A. Efros, Stella X. Yu	This paper adopts a non-parametric approach for visual recognition by optimizing feature embeddings instead of parametric classifiers.
394	Combining 3D Model Contour Energy and Keypoints for Object Tracking	Bogdan Bugaev, Anton Kryshchenko, Roman Belov	We present a new combined approach for monocular model-based 3D tracking.
395	Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation	Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing	To address these challenges for unsupervised video segmentation, we develop a novel saliency estimation technique as well as a novel neighborhood graph, based on optical flow and edge cues.
396	Pairwise Confusion for Fine-Grained Visual Classification	Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell, Nikhil Naik	In this work, we address this problem using a novel optimization procedure for the end-to-end neural network training on FGVC tasks.
397	Modular Generative Adversarial Networks	Bo Zhao, Bo Chang, Zequn Jie, Leonid Sigal	Inspired by module networks, this paper propose ModularGAN for multi-domain image-to-image translation that consists of several reusable and compatible modules of different functions.
398	Simultaneous 3D Reconstruction for Water Surface and Underwater Scene	Yiming Qian, Yinqiang Zheng, Minglun Gong, Yee-Hong Yang	This paper presents the first approach for simultaneously recovering the 3D shape of both the wavy water surface and the moving underwater scene.
399	Temporal Relational Reasoning in Videos	Bolei Zhou, Alex Andonian, Aude Oliva, Antonio Torralba	In this paper, we introduce an effective and interpretable network module, the Temporal Relation Network (TRN), designed to learn and reason about temporal dependencies between video frames at multiple time scales.
400	YouTube-VOS: Sequence-to-Sequence Video Object Segmentation	Ning Xu, Linjie Yang, Yuchen Fan, Jianchao Yang, Dingcheng Yue, Yuchen Liang, Brian Price, Scott Cohen, Thomas Huang	Based on this dataset, we propose a novel sequence-to-sequence network to fully exploit long-term spatial-temporal information in videos for segmentation. To solve this problem, we build a new large-scale video object segmentation dataset called YouTube Video Object Segmentation dataset (YouTube-VOS).
401	Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input	David Harwath, Adria Recasens, Didac Suris, Galen Chuang, Antonio Torralba, James Glass	In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to.
402	Women also Snowboard: Overcoming Bias in Captioning Models	Lisa Anne Hendricks, Kaylee Burns, Kate Saenko, Trevor Darrell, Anna Rohrbach	In this work we investigate generation of gender-specific caption words (e.g. man, woman) based on the person’s appearance or the image context.
403	Graph Distillation for Action Detection with Privileged Modalities	Zelun Luo, Jun-Ting Hsieh, Lu Jiang, Juan Carlos Niebles, Li Fei-Fei	We propose a technique that tackles action detection in multimodal videos under a realistic and challenging condition in which only limited training data and partially observed modalities are available.
404	Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences	Mohammed E. Fathy, Quoc-Huy Tran, M. Zeeshan Zia, Paul Vernaza, Manmohan Chandraker	We propose concrete CNN architectures employing these ideas, and evaluate them on multiple datasets for 2D and 3D geometric matching as well as optical flow, demonstrating state-of-the-art results and generalization across datasets.
405	Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing	Dong Yang, Jian Sun	In this paper, we propose a novel deep learning approach for single image dehazing by learning dark channel and transmission priors.
406	Deep Component Analysis via Alternating Direction Neural Networks	Calvin Murdock, MingFang Chang, Simon Lucey	For inference, we propose a differentiable optimization algorithm implemented using recurrent Alternating Direction Neural Networks (ADNNs) that enable parameter learning using standard backpropagation.
407	SDC-Net: Video prediction using spatially-displaced convolution	Fitsum A. Reda, Guilin Liu, Kevin J. Shih, Robert Kirby, Jon Barker, David Tarjan, Andrew Tao, Bryan Catanzaro	We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows.
408	Exploiting temporal information for 3D human pose estimation	Mir Rayat Imtiaz Hossain, James J. Little	In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses.
409	Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery	Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang	In this paper, we present an efficient convolutional neural network (CNN) based method, which can jointly select the optimal CSS from a candidate dataset and learn a mapping to recover HSI from a single RGB image captured with this algorithmically selected camera.
410	ADVISE: Symbolism and External Knowledge for Decoding Advertisements	Keren Ye, Adriana Kovashka	We show how to use symbolic references to better understand the meaning of an ad.
411	Person Search via A Mask-guided Two-stream CNN Model	Di Chen, Shanshan Zhang, Wanli Ouyang, Jian Yang, Ying Tai	In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification~(re-ID).
412	GridFace: Face Rectification via Learning Local Homography Transformations	Erjin Zhou, Zhimin Cao, Jian Sun	In this paper, we propose a novel method, called GridFace, to reduce facial geometric variations and improve the recognition performance.
413	Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior	Sijia Cai, Wangmeng Zuo, Larry S. Davis, Lei Zhang	To leverage the plentiful web-crawled videos to improve the performance of video summarization, we present a generative modelling framework to learn the latent semantic video representations to bridge the benchmark data and web data.
414	Compound Memory Networks for Few-shot Video Classification	Linchao Zhu, Yi Yang	In this paper, we propose a new memory network structure for few-shot video classification by making the following contributions.
415	Contextual-based Image Inpainting: Infer, Match, and Translate	Yuhang Song, Chao Yang, Zhe Lin, Xiaofeng Liu, Qin Huang, Hao Li, C.-C. Jay Kuo	To this end, we propose a learning-based approach to generate visually coherent completion given a high-resolution image with missing components.
416	Interpretable Intuitive Physics Model	Tian Ye, Xiaolong Wang, James Davidson, Abhinav Gupta	Inspired by this observation, we propose an interpretable intuitive physics model where specific dimensions in the bottleneck layers correspond to different physical properties.
417	Polarimetric Three-View Geometry	Lixiong Chen, Yinqiang Zheng, Art Subpa-asa, Imari Sato	We demonstrate that, in a multi-view system, the polarization phase obtained for a surface point is induced from one of the two pencils of planes: one by specular reflections with its axis aligned with the incident light; one by diffusive reflections with its axis aligned with the surface normal.
418	Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation	Xin Wang, Wenhan Xiong, Hongmin Wang, William Yang Wang	In this paper, we take a radical approach to bridge the gap between synthetic studies and real-world practices—We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task.
419	Weakly-supervised 3D Hand Pose Estimation from Monocular RGB Images	Yujun Cai, Liuhao Ge, Jianfei Cai, Junsong Yuan	Particularly, we propose a weakly-supervised method, adaptating from fully-annotated synthetic dataset to weakly-labeled real-world dataset with the aid of a depth regularizer, which generates depth maps from predicted 3D pose and serves as weak supervision for 3D pose regression.
420	T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks	Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai	We propose a framework, trained on synthetic image-depth pairs and unpaired real images, that comprises an image translation network for enhancing realism of input images, followed by a depth prediction network.
421	Instance-level Human Parsing via Part Grouping Network	Ke Gong, Xiaodan Liang, Yicheng Li, Yimin Chen, Ming Yang, Liang Lin	In this work, we make the first attempt to explore a detection-free Part Grouping Network (PGN) for efficiently parsing multiple people in an image in a single pass.
422	TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes	Shangbang Long, Jiaqiang Ruan, Wenjie Zhang, Xin He, Wenhao Wu, Cong Yao	To tackle this problem, we propose a more flexible representation for scene text, termed as extit{TextSnake}, which is able to effectively represent text instances in horizontal, oriented and curved forms.
423	PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors	Haowen Deng, Tolga Birdal, Slobodan Ilic	We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry.
424	Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association	Dapeng Chen, Hongsheng Li, Xihui Liu, Yantao Shen, Jing Shao, Zejian Yuan, Xiaogang Wang	In this paper, we propose to exploit natural language description as additional training supervisions for more effective features.
425	AMC: AutoML for Model Compression and Acceleration on Mobile Devices	Yihui He, Ji Lin, Zhijian Liu, Hanrui Wang, Li-Jia Li, Song Han	In this paper, we propose AutoML for Model Compression (AMC) which leverages reinforcement learning to efficiently sample the design space and can improve the model compression quality.
426	Robust fitting in computer vision: easy or hard?	Tat-Jun Chin, Zhipeng Cai, Frank Neumann	To shed light on these issues, we present several computational hardness results for consensus maximisation.
427	Graph Adaptive Knowledge Transfer for Unsupervised Domain Adaptation	Zhengming Ding, Sheng Li, Ming Shao, Yun Fu	To address that issue, we develop a novel Graph Adaptive Knowledge Transfer (GAKT) model to jointly optimize target labels and domain-free features in a unified framework.
428	Single Image Intrinsic Decomposition without a Single Intrinsic Image	Wei-Chiu Ma, Hang Chu, Bolei Zhou, Raquel Urtasun, Antonio Torralba	In this paper, we propose to bring the best of both worlds.
429	Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders	Ananya Harsh Jha, Saket Anand, Maneesh Singh, VSR Veeravasarapu	In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity labels. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task.
430	Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental States	Guosheng Hu, Li Liu, Yang Yuan, Zehao Yu, Yang Hua, Zhihong Zhang, Fumin Shen, Ling Shao, Timothy Hospedales, Neil Robertson, Yongxin Yang	We address subtle expression recognition through convolutional neural networks (CNNs) by developing multi-task learning (MTL) to effectively leverage a side task: facial landmark detection.
431	SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation	Wenqiang Xu, Yonglu Li, Cewu Lu	By combining the advantages of 3D scanning, reasoning, and GAN-based domain adaptation techniques, we introduce a novel pipeline named SRDA to obtain large quantities of training samples with very minor effort. To evaluate our performance, we build three representative scenes and a new dataset, with 3D models of various common objects categories and annotated real-world scene images.
432	DeepWrinkles: Accurate and Realistic Clothing Modeling	Zorah Lahner, Daniel Cremers, Tony Tung	We present a novel method to generate accurate and realistic clothing deformation from real data capture.
433	Recovering 3D Planes from a Single Image via Convolutional Neural Networks	Fengting Yang, Zihan Zhou	In this paper, we study the problem of recovering 3D planar surfaces from a single image of man-made environment.
434	Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks	Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran Varanasi, Didier Stricker	We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs.
435	A Geometric Perspective on Structured Light Coding	Mohit Gupta, Nikhil Nakhate	We present a mathematical framework for analysis and design of high performance structured light (SL) coding schemes.
436	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation	Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam	In this work, we propose to combine the advantages from both methods.
437	Robust image stitching with multiple registrations	Charles Herrmann, Chen Wang, Richard Strong Bowen, Emil Keyder, Michael Krainin, Ce Liu, Ramin Zabih	We propose instead the use of multiple registrations, permitting regions of the image at different depths to be captured with greater accuracy.
438	Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network	Xinjing Cheng, Peng Wang, Ruigang Yang	In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for depth prediction.
439	Object-centered image stitching	Charles Herrmann, Chen Wang, Richard Strong Bowen, Emil Keyder, Ramin Zabih	We therefore take an object-centered approach to the problem, leveraging recent advances in object detection.
440	Learning to Dodge A Bullet: Concyclic View Morphing via Deep Learning	Shi Jin, Ruiynag Liu, Yu Ji, Jinwei Ye, Jingyi Yu	In this paper, we present a learning-based solution that is capable of producing the bullet-time effect from only a small set of images.
441	CTAP: Complementary Temporal Action Proposal Generation	Jiyang Gao, Kan Chen, Ram Nevatia	Based on the complementary characteristics of these two methods, we propose a novel Complementary Temporal Action Proposal (CTAP) generator.
442	Effective Use of Synthetic Data for Urban Scene Semantic Segmentation	Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez	In this paper, we introduce a drastically different way to handle synthetic images that does not require seeing any real images at training time.
443	ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems	Yinda Zhang, Sameh Khamis, Christoph Rhemann, Julien Valentin, Adarsh Kowdle, Vladimir Tankovich, Michael Schoenberg, Shahram Izadi, Thomas Funkhouser, Sean Fanello	In this paper we present ActiveStereoNet, the first deep learning solution for active stereo systems.
444	ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids	Dinesh Jayaraman, Ruohan Gao, Kristen Grauman	We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation.
445	Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency	Xingyi Zhou, Arjun Karpur, Chuang Gan, Linjie Luo, Qixing Huang	In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image.
446	Learning Discriminative Video Representations Using Adversarial Perturbations	Jue Wang, Anoop Cherian	In this paper, we propose to use such perturbations for improving the robustness of video representations. Using the original data features from the full video sequence and their perturbed counterparts, as two separate bags, we develop a binary classification problem that learns a set of discriminative hyperplanes — as a subspace — that will separate the two bags from each other.
447	BSN: Boundary Sensitive Network for Temporal Action Proposal Generation	Tianwei Lin, Xu Zhao, Haisheng Su, Chongjing Wang, Ming Yang	To address these difficulties, we introduce an effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts “local to global” fashion.
448	In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person Video	Yin Li, Miao Liu, James M. Rehg	We propose a novel deep model for joint gaze estimation and action recognition in First Person Vision.
449	Compositional Learning for Human Object Interaction	Keizo Kato, Yin Li, Abhinav Gupta	In this paper, we explore the problem of zero-shot learning of human-object interactions. We also provide benchmarks on several dataset for zero-shot learning including both image and video.
450	Open-World Stereo Video Matching with Deep RNN	Yiran Zhong, Hongdong Li, Yuchao Dai	In this paper, we propose a novel deep Recurrent Neural network (RNN) that takes a continuous (possibly previously unseen) stereo video as input, and directly predict a depth-map without of any pre-training process.
451	stagNet: An Attentive Semantic RNN for Group Activity Recognition	Mengshi Qi, Jie Qin, Annan Li, Yunhong Wang, Jiebo Luo, Luc Van Gool	We propose a novel attentive semantic recurrent neural network (RNN), namely stagNet, for understanding group activities in videos, based on the spatio-temporal attention and semantic graph.
452	Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural Network	Jinseok Park, Donghyeon Cho, Wonhyuk Ahn, Heung-Kyu Lee	This paper proposes a novel deep convolutional neural network for double JPEG detection using statistical histogram features from each block with a vectorized quantization table. We collected real-world JPEG images from the image forensic service and generated a new double JPEG dataset with 1120 quantization tables to train the network.
453	Deep High Dynamic Range Imaging with Large Foreground Motions	Shangzhe Wu, Jiarui Xu, Yu-Wing Tai, Chi-Keung Tang	This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions.
454	Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching	Hanyu Wang, Jianwei Guo, Dong-Ming Yan, Weize Quan, Xiaopeng Zhang	In this paper, we present a novel deep learning framework that derives discriminative local descriptors for 3D surface shapes.
455	Learning Class Prototypes via Structure Alignment for Zero-Shot Recognition	Huajie Jiang, Ruiping Wang, Shiguang Shan, Xilin Chen	To tackle such problem, we propose a coupled dictionary learning approach to align the visual-semantic structures using the class prototypes, where the discriminative information lying in the visual space is utilized to improve the less discriminative semantic space.
456	CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images	Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R. Scott, Dinglong Huang	We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled rawly from the Internet by using text queries, without any human annotation.
457	A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising	Jun Xu, Lei Zhang, David Zhang	In this paper, we develop a trilateral weighted sparse coding (TWSC) scheme for robust real-world image denoising.
458	Linear Span Network for Object Skeleton Detection	Chang Liu, Wei Ke, Fei Qin, Qixiang Ye	In this paper, we first re-visit the implementation of HED, the essential principle of which can be ideally described with a linear reconstruction model.
459	DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs	Shi Yan, Chenglei Wu, Lizhen Wang, Feng Xu, Liang An, Kaiwen Guo, Yebin Liu	We propose a cascaded Depth Denoising and Refinement Network (DDRNet) to tackle this problem by leveraging the multi-frame fused geometry and the accompanying high quality color image through a joint training strategy.
460	ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes	Taihong Xiao, Jiapeng Hong, Jinwen Ma	To address these limitations, we propose a novel model which receives two images of opposite attributes as inputs.
461	Progressive Structure from Motion	Alex Locher, Michal Havlena, Luc Van Gool	In this paper we propose a new reconstruction pipeline working in a progressive manner rather than in a batch processing scheme.
462	GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction	Li Jiang, Shaoshuai Shi, Xiaojuan Qi, Jiaya Jia	In this paper, we present a framework for reconstructing a point-based 3D model of an object from a single view image.
463	Viewpoint Estimation—Insights & Model	Gilad Divon, Ayellet Tal	This paper addresses the problem of viewpoint estimation of an object in a given image.
464	Super-Resolution and Sparse View CT Reconstruction	Guangming Zang, Mohamed Aly, Ramzi Idoughi, Peter Wonka, Wolfgang Heidrich	We present a flexible framework for robust computed tomography (CT) reconstruction with a specific emphasis on recovering thin 1D and 2D manifolds embedded in 3D volumes.
465	NNEval: Neural Network based Evaluation Metric for Image Captioning	Naeha Sharif, Lyndon White, Mohammed Bennamoun, Syed Afaq Ali Shah	In this paper, we present the first learning-based metric to evaluate image captions.
466	Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based Refinement	Minhyeok Heo, Jaehan Lee, Kyung-Rae Kim, Han-Ul Kim, Chang-Su Kim	We propose a monocular depth estimation algorithm, which extracts a depth map from a single image, based on whole strip masking (WSM) and reliability-based refinement.
467	Dynamic Filtering with Large Sampling Field for ConvNets	Jialin Wu, Dai Li, Yu Yang, Chandrajit Bajaj, Xiangyang Ji	We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbour regions.
468	SaaS: Speed as a Supervisor for Semi-supervised Learning	Safa Cicek, Alhussein Fawzi, Stefano Soatto	We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels.
469	AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos	Zheng Shou, Hang Gao, Lei Zhang, Kazuyuki Miyazawa, Shih-Fu Chang	We propose a novel Outer-Inner-Contrastive (OIC) loss to automatically discover the needed segment-level supervision for training such a boundary predictor.
470	Local Spectral Graph Convolution for Point Set Feature Learning	Chu Wang, Babak Samari, Kaleem Siddiqi	In the present article, we propose to overcome this limitation by using spectral graph convolution on a local graph, combined with a novel graph pooling strategy.
471	Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights	Arun Mallya, Dillon Davis, Svetlana Lazebnik	This work presents a method for adapting a single, fixed deep neural network to multiple tasks without affecting performance on already learned tasks.
472	VideoMatch: Matching based Video Object Segmentation	Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing	To address this issue, we develop a novel matching based algorithm for video object segmentation.
473	Wasserstein Divergence for GANs	Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc Van Gool	As a concrete application, we introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate W-div through optimization.
474	Semi-supervised FusedGAN for Conditional Image Generation	Navaneeth Bodla, Gang Hua, Rama Chellappa	We present FusedGAN, a deep network for conditional image synthesis with controllable sampling of diverse images.
475	Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms	Arjun Nitin Bhagoji, Warren He, Bo Li, Dawn Song	In this paper, we propose novel Gradient Estimation black-box attacks for adversaries with query access to the target model’s class probabilities, which do not rely on transferability.
476	PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model	George Papandreou, Tyler Zhu, Liang-Chieh Chen, Spyros Gidaris, Jonathan Tompson, Kevin Murphy	We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model.
477	Context Refinement for Object Detection	Zhe Chen, Shaoli Huang, Dacheng Tao	To address this problem, we propose a context refinement algorithm that explores rich contextual information to better refine each proposed region.
478	Attention-GAN for Object Transfiguration in Wild Images	Xinyuan Chen, Chang Xu, Xiaokang Yang, Dacheng Tao	This paper studies the object transfiguration problem in wild images.
479	Pose Guided Human Video Generation	Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin	In this paper, we propose a pose guided method to synthesize human videos in a disentangled way: plausible motion prediction and coherent appearance generation.
480	Exploring the Limits of Weakly Supervised Pretraining	Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten	In this paper, we present a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images.
481	Exploiting Vector Fields for Geometric Rectification of Distorted Document Images	Gaofeng MENG, Yuanqi SU, Ying WU, Shiming XIANG, Chunhong PAN	This paper proposes a segment-free method for geometric rectification of a distorted document image captured by a hand-held camera.
482	Task-driven Webpage Saliency	Quanlong Zheng, Jianbo Jiao, Ying Cao, Rynson W.H. Lau	In this paper, we present an end-to-end learning framework for predicting task-driven visual saliency on webpages.
483	Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation	Chaowei Xiao, Ruizhi Deng, Bo Li, Fisher Yu, Mingyan Liu, Dawn Song	In this paper, we aim to characterize adversarial examples based on spatial context information in segmentation.
484	DYAN: A Dynamical Atoms-Based Network For Video Prediction	Wenqian Liu, Abhishek Sharma, Octavia Camps, Mario Sznaier	In this paper, we introduce DYAN, a novel network with very few parameters and easy to train, which produces accurate, high quality frame predictions, significantly faster than previous approaches.
485	SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters	Yifan Xu, Tianqi Fan, Mingye Xu, Long Zeng, Yu Qiao	Towards this we propose a novel convolutional architecture, termed SpiderCNN, to efficiently extract geometric features from point clouds.
486	Hard-Aware Point-to-Set Deep Metric for Person Re-identification	Rui Yu, Zhiyong Dou, Song Bai, Zhaoxiang Zhang, Yongchao Xu, Xiang Bai	To solve this problem, we propose a Hard-Aware Point-to-Set (HAP2S) loss with a soft hard-mining scheme.
487	Coded Two-Bucket Cameras for Computer Vision	Mian Wei, Navid Sarhangnejad, Zhengfan Xia, Nikita Gusev, Nikola Katic, Roman Genov, Kiriakos N. Kutulakos	We introduce coded two-bucket (C2B) imaging, a new operating principle for computational sensors with applications in active 3D shape estimation and coded-exposure imaging.
488	Egocentric Activity Prediction via Event Modulated Attention	Yang Shen, Bingbing Ni, Zefan Li, Ning Zhuang	This work explicitly addresses these issues by proposing an asynchronous gaze-event driven attentive activity prediction network.
489	Real-Time MDNet	Ilchae Jung, Jeany Son, Mooyeol Baek, Bohyung Han	We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet).
490	Image Generation from Sketch Constraint Using Contextual GAN	Yongyi Lu, Shangzhe Wu, Yu-Wing Tai, Chi-Keung Tang	In this paper we investigate image generation guided by hand sketch.
491	Real-Time Hair Rendering using Sequential Adversarial Networks	Lingyu Wei, Liwen Hu, Vladimir Kim, Ersin Yumer, Hao Li	We present an adversarial network for rendering photorealistic hair as an alternative to conventional computer graphics pipelines.
492	Sparsely Aggregated Convolutional Networks	Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori, Ping Tan	We propose a new internal connection structure which aggregates only a sparse set of previous outputs at any given depth.
493	Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors	Dmitry Baranchuk, Artem Babenko, Yury Malkov	In this paper, we argue that the potential of the simple inverted index was not fully exploited in previous works and advocate its usage both for the highly-entangled deep descriptors and relatively disentangled SIFT descriptors.
494	Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation	Zhenyu Zhang, Zhen Cui, Chunyan Xu, Zequn Jie, Xiang Li, Jian Yang	In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks.
495	Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network	Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn	In this paper, we address this issue by proposing an accurate and lightweight deep network for image super-resolution.
496	Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks	Filippos Kokkinos, Stamatios Lefkimmiatis	This improvement in reconstruction quality is attributed to the principled way we design our network architecture, which also requires fewer trainable parameters than the current state-of-the-art deep network solution.
497	Modality Distillation with Multiple Stream Networks for Action Recognition	Nuno C. Garcia, Pietro Morerio, Vittorio Murino	This paper presents a new approach for multimodal video action recognition, developed within the unified frameworks of distillation and privileged information, named generalized distillation.
498	Direct Sparse Odometry With Rolling Shutter	David Schubert, Nikolaus Demmel, Vladyslav Usenko, Jorg Stuckler, Daniel Cremers	In this paper, we propose a novel direct monocular VO method that incorporates a rolling-shutter model.
499	Multi-Class Model Fitting by Energy Minimization and Mode-Seeking	Daniel Barath, Jiri Matas	Considering that a group of outliers may form spatially coherent structures in the data, we propose a cross-validation-based technique removing statistically insignificant instances.
500	Model-free Consensus Maximization for Non-Rigid Shapes	Thomas Probst, Ajad Chhatkuli, Danda Pani Paudel, Luc Van Gool	In this paper, we formulate the model-free consensus maximization as an Integer Program in a graph using ‘rules’ on measurements.
501	How good is my GAN?	Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari	In this paper we introduce two measures based on image classification—GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively.
502	Pose Partition Networks for Multi-Person Pose Estimation	Xuecheng Nie, Jiashi Feng, Junliang Xing, Shuicheng Yan	This paper proposes a novel Pose Partition Network (PPN) to address the challenging multi-person pose estimation problem.
503	3D-CODED: 3D Correspondences by Deep Deformation	Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry	We present a new deep learning approach for matching deformable shapes by introducing Shape Deformation Networks which jointly encode 3D shapes and correspondences.
504	Interpretable Basis Decomposition for Visual Explanation	Bolei Zhou, Yiyou Sun, David Bau, Antonio Torralba	In this work we propose a new framework called Interpretable Basis Decomposition for providing visual explanations for classification networks.
505	Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry	Nan Yang, Rui Wang, Jorg Stuckler, Daniel Cremers	In this paper, we propose to leverage deep monocular depth prediction to overcome limitations of geometry-based monocular visual odometry.
506	HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision	Xiaokun Wu, Daniel Finnegan, Eamonn O’Neill, Yong-Liang Yang	This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision.
507	Partial Adversarial Domain Adaptation	Zhangjie Cao, Lijia Ma, Mingsheng Long, Jianmin Wang	This paper introduces partial domain adaptation as a new domain adaptation scenario, which relaxes the fully shared label space assumption to that the source label space subsumes the target label space.
508	ExFuse: Enhancing Feature Fusion for Semantic Segmentation	Zhenli Zhang, Xiangyu Zhang, Chao Peng, Xiangyang Xue, Jian Sun	Based on this observation, we propose a new framework, named ExFuse, to bridge the gap between low-level and high-level features thus significantly improve the segmentation quality by 4.0% in total.
509	Audio-Visual Event Localization in Unconstrained Videos	Yapeng Tian, Jing Shi, Bochen Li, Zhiyao Duan, Chenliang Xu	In this paper, we introduce a novel problem of audio-visual event localization in unconstrained videos.
510	Understanding Degeneracies and Ambiguities in Attribute Transfer	Attila Szabo, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro	To address the shortcut problem, we introduce novel constraints on image pairs and triplets and show their effectiveness both analytically and experimentally.
511	Relaxation-Free Deep Hashing via Policy Gradient	Xin Yuan, Liangliang Ren, Jiwen Lu, Jie Zhou	In this paper, we propose a simple yet effective relaxation-free method to learn more effective binary codes via policy gradient for scalable image search.
512	How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization	Yandong Li, Liqiang Wang, Tianbao Yang, Boqing Gong	In this paper, we propose a novel probabilistic model, built upon SeqDPP, to dynamically control the time span of a video segment upon which the local diversity is imposed.
513	Question Type Guided Attention in Visual Question Answering	Yang Shi, Tommaso Furlanello, Sheng Zha, Animashree Anandkumar	In this work, we propose Question Type-guided Attention (QTA).
514	Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics	Matthias Kummerer, Thomas S. A. Wallis, Matthias Bethge	Instead, we propose a principled approach to solve the benchmarking problem by separating the notions of saliency models, maps and metrics.
515	A Unified Framework for Multi-View Multi-Class Object Pose Estimation	Chi Li, Jin Bai, Gregory D. Hager	In this work, we present a scalable framework for accurately inferring six Degree-of-Freedom (6-DoF) pose for a large number of object classes from single or multiple views.
516	A New Large Scale Dynamic Texture Dataset with Application to ConvNet Understanding	Isma Hadji, Richard P. Wildes	This paper introduces a new large scale dynamic texture dataset.
517	Dynamic Task Prioritization for Multitask Learning	Michelle Guo, Albert Haque, De-An Huang, Serena Yeung, Li Fei-Fei	We propose dynamic task prioritization for multitask learning.
518	Deep Feature Factorization For Concept Discovery	Edo Collins, Radhakrishna Achanta, Sabine Susstrunk	We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images.
519	Diverse feature visualizations reveal invariances in early layers of deep neural networks	Santiago A. Cadena, Marissa A. Weis, Leon A. Gatys, Matthias Bethge, Alexander S. Ecker	Here we propose a method to discover invariances in the responses of hidden layer units of deep neural networks.
520	Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification	Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto	We address the problem of person re-identification from commodity depth sensors.
521	NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications	Tien-Ju Yang, Andrew Howard, Bo Chen, Xiao Zhang, Alec Go, Mark Sandler, Vivienne Sze, Hartwig Adam	This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget.
522	Estimating Depth from RGB and Sparse Sensing	Zhao Chen, Vijay Badrinarayanan, Gilad Drozdov, Andrew Rabinovich	We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels.
523	Grounding Visual Explanations	Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata	To overcome this limitation, we propose a phrase-critic model to refine generated candidate explanations augmented with flipped phrases which we use as negative examples while training.
524	End-to-End Incremental Learning	Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Cordelia Schmid, Karteek Alahari	We address this issue with our approach to learn deep neural networks incrementally, using new data and only a small exemplar set corresponding to samples from the old classes.
525	Toward Scale-Invariance and Position-Sensitive Region Proposal Networks	Hsueh-Fu Lu, Xiaofei Du, Ping-Lin Chang	In this work, we propose an advanced object proposal network in favour of translation-invariance for objectness classification, translation-variance for bounding box regression, large effective receptive fields for capturing global context and scale-invariance for dealing with a range of object sizes from extremely small to large.
526	Deep Regression Tracking with Shrinkage Loss	Xiankai Lu, Chao Ma, Bingbing Ni, Xiaokang Yang, Ian Reid, Ming-Hsuan Yang	To balance training data, we propose a novel shrinkage loss to penalize the importance of easy training data.
527	A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers	Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Jian Tang, Wujie Wen, Makan Fardad, Yanzhi Wang	To mitigate these limitations, we present a systematic weight pruning framework of DNNs using the alternating direction method of multipliers (ADMM).
528	Adversarial Open-World Person Re-Identification	Xiang Li, Ancong Wu, Wei-Shi Zheng	In this work, we introduce a deep open-world group-based person re-id model based on adversarial learning to alleviate the attack problem caused by similar non-target people.
529	Conditional Image-Text Embedding Networks	Bryan A. Plummer, Paige Kordas, M. Hadi Kiapour, Shuai Zheng, Robinson Piramuthu, Svetlana Lazebnik	This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model.
530	DeepIM: Deep Iterative Matching for 6D Pose Estimation	Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox	In this work, we propose a novel deep neural network for 6D pose matching named DeepIM.
531	Dist-GAN: An Improved GAN using Distance Constraints	Ngoc-Trung Tran, Tuan-Anh Bui, Ngai-Man Cheung	We introduce effective training algorithms for Generative Adversarial Networks (GAN) to alleviate mode collapse and gradient vanishing.
532	Pivot Correlational Neural Network for Multimodal Video Categorization	Sunghun Kang, Junyeong Kim, Hyunsoo Choi, Sungjin Kim, Chang D. Yoo	This paper considers an architecture for multimodal video categorization referred to as Pivot Correlational Neural Network (Pivot CorrNN).
533	Generative Domain-Migration Hashing for Sketch-to-Image Retrieval	Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc Van Gool	In this work, we propose a Generative Domain-migration Hashing (GDH) approach, which for the first time generates hashing codes from synthetic natural images that are migrated from sketches.
534	TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights	Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Jie Qin, Ling Shao, Heng Tao Shen	In this work, we propose a Ternary-Binary Network (TBN), which provides an efficient approximation to standard CNNs.
535	Multi-object Tracking with Neural Gating Using Bilinear LSTM	Chanho Kim, Fuxin Li, James M. Rehg	In this paper, we propose a novel recurrent network model, the bilinear LSTM, in order to improve long-term appearance models via a recurrent network.
536	Highly-Economized Multi-View Binary Compression for Scalable Image Clustering	Zheng Zhang, Li Liu, Jie Qin, Fan Zhu, Fumin Shen, Yong Xu, Ling Shao, Heng Tao Shen	To tackle this challenge, this paper introduces a novel approach named Highly-economized Scalable Image Clustering (HSIC) that radically surpasses conventional image clustering methods via binary compression.
537	Part-Aligned Bilinear Representations for Person Re-Identification	Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei, Kyoung Mu Lee	In this paper, we propose a network that learns a part-aligned representation for person re-identification.
538	End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNN	Yunlong Wang, Fei Liu, Zilei Wang, Guangqi Hou, Zhenan Sun, Tieniu Tan	In this paper, an end-to-end deep learning framework is proposed to solve these problems by exploring Pseudo 4DCNN.
539	Action Anticipation with RBF Kernelized Feature Mapping RNN	Yuge Shi, Basura Fernando, Richard Hartley	We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called ame.
540	Joint Blind Motion Deblurring and Depth Estimation of Light Field	Dongwoo Lee, Haesol Park, In Kyu Park, Kyoung Mu Lee	In this paper, we propose a novel algorithm to estimate all blur model variables jointly, including latent sub-aperture image, camera motion, and scene depth from the blurred 4D light field.
541	Learning to Navigate for Fine-grained Classification	Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang	To handle this circumstance, we propose a novel self-supervision mechanism to effectively localize informative regions without the need of fine-grained bounding-box/part annotations.
542	Specular-to-Diffuse Translation for Multi-View Reconstruction	Shihao Wu, Hui Huang, Tiziano Portenier, Matan Sela, Daniel Cohen-Or, Ron Kimmel, Matthias Zwicker	To alleviate this restriction, we introduce S2Dnet, a generative adversarial network for transferring multiple views of objects with specular reflection into diffuse ones, so that multi-view reconstruction methods can be applied more effectively. In addition, we carefully design and generate a large synthetic training data set using physically-based rendering.
543	Clustering Convolutional Kernels to Compress Deep Neural Networks	Sanghyun Son, Seungjun Nah, Kyoung Mu Lee	In this paper, we propose a novel method to compress CNNs by reconstructing the network from a small set of spatial convolution kernels.
544	Scale Aggregation Network for Accurate and Efficient Crowd Counting	Xinkun Cao, Zhipeng Wang, Yanyun Zhao, Fei Su	In this paper, we propose a novel encoder-decoder network, called extit{Scale Aggregation Network (SANet)}, for accurate and efficient crowd counting.
545	Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data	Yabin Zhang, Hui Tang, Kui Jia	To address this issue, we propose in this paper a new deep FGVC model termed MetaFGNet.
546	Sampling Algebraic Varieties for Robust Camera Autocalibration	Danda Pani Paudel, Luc Van Gool	During the BnB search, we exploit the theory of sampling algebraic varieties, to test the positivity of any polynomial within a parameter’s interval, i.e. outliers with certainty.
547	Stacked Cross Attention for Image-Text Matching	Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, Xiaodong He	In this paper, we study the problem of image-text matching.
548	Data-Driven Sparse Structure Selection for Deep Neural Networks	Zehao Huang, Naiyan Wang	In this paper, we propose a simple and effective framework to learn and prune deep models in an end-to-end manner.
549	DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks	Weixuan Chen, Daniel McDuff	We propose the first end-to-end system for video-based measurement of heart and breathing rate using a deep convolutional network.
550	Attribute-Guided Face Generation Using Conditional CycleGAN	Yongyi Lu, Yu-Wing Tai, Chi-Keung Tang	To address this problem, we condition the CycleGAN and propose conditional CycleGAN, which is designed to 1) handle unpaired training data because the training low/high-res and high-res attribute images may not necessarily align with each other, and to 2) allow easy control of the appearance of the generated face via the input attributes.
551	On the Solvability of Viewing Graphs	Matthew Trager, Brian Osserman, Jean Ponce	We study characterizations of “solvable” viewing graphs, and present several new results that can be applied to determine which pairs of views may be used to recover all camera parameters.
552	A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws	Gilles Simon, Antoine Fond, Marie-Odile Berger	We show that, in images of man-made environments, the horizon line can usually be hypothesized based on an a contrario detection of second-order grouping events.
553	Deep Volumetric Video From Very Sparse Multi-View Performance Capture	Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing, Chloe LeGendre, Linjie Luo, Chongyang Ma, Hao Li	We present a deep learning-based volumetric capture approach for performance capture using a passive and highly sparse multi-view capture system.
554	Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes	Fangneng Zhan, Shijian Lu, Chuhui Xue	This paper presents a novel image synthesis technique that aims to generate a large amount of annotated scene text images for training accurate and robust scene text detection and recognition models.
555	Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping	Chuhui Xue, Shijian Lu, Fangneng Zhan	This paper presents a scene text detection technique that exploits bootstrapping and text border semantics for accurate localization of texts in scenes.
556	RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments	Tobias Fischer, Hyung Jin Chang, Yiannis Demiris	In this work, we consider the problem of robust gaze estimation in natural environments.
557	Deep Video Generation, Prediction and Completion of Human Action Sequences	Haoye Cai, Chunyan Bai, Yu-Wing Tai, Chi-Keung Tang	In this paper, we focus on human action videos, and propose a general, two-stage deep framework to generate human action videos with no constraints or arbitrary number of constraints, which uniformly address the three problems: video generation given no input frames, video prediction given the first few frames, and video completion given the first and last frames.
558	Quantization Mimic: Towards Very Tiny CNN for Object Detection	Yi Wei, Xinyu Pan, Hongwei Qin, Wanli Ouyang, Junjie Yan	In this paper, we propose a simple and general framework for training very tiny CNNs for object detection.
559	Deep Structure Inference Network for Facial Action Unit Recognition	Ciprian Corneanu, Meysam Madadi, Sergio Escalera	In this paper, we propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages.
560	Deep Shape Matching	Filip Radenovic, Giorgos Tolias, Ondrej Chum	We cast shape matching as metric learning with convolutional networks.
561	Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses	Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann	In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.
562	Efficient Semantic Scene Completion Network with Spatial Group Convolution	Jiahui Zhang, Hao Zhao, Anbang Yao, Yurong Chen, Li Zhang, Hongen Liao	We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.
563	Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification	Yang Du, Chunfeng Yuan, Bing Li, Lili Zhao, Yangxi Li, Weiming Hu	To address this, we propose an effective interaction-aware self-attention model inspired by PCA to learn attention maps.
564	Deep Texture and Structure Aware Filtering Network for Image Smoothing	Kaiyue Lu, Shaodi You, Nick Barnes	In this paper, we tackle the natural deficiency of existing methods, that they cannot properly distinguish textures and structures with similar low-level appearance. To this end, we generate a large dataset by blending natural textures with clean structure-only images, and then build a texture prediction network (TPN) that predicts location and magnitude of textures.
565	Learning to Solve Nonlinear Least Squares for Monocular Stereo	Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J. Davison	In this paper, we propose a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.
566	Unsupervised Class-Specific Deblurring	Thekke Madam Nimisha, Kumar Sunil, A. N. Rajagopalan	In this paper, we present an end-to-end deblurring network designed specifically for a class of data.
567	VSO: Visual Semantic Odometry	Konstantinos-Nektarios Lianos, Johannes L. Schonberger, Marc Pollefeys, Torsten Sattler	In this paper, we propose a novel visual semantic odometry (VSO) framework to enable medium-term continuous tracking of points using semantics.
568	Semantic Match Consistency for Long-Term Visual Localization	Carl Toft, Erik Stenborg, Lars Hammarstrand, Lucas Brynte, Marc Pollefeys, Torsten Sattler, Fredrik Kahl	In this paper, we present a method for scoring the individual correspondences by exploiting semantic information about the query image and the scene.
569	Learning Priors for Semantic 3D Reconstruction	Ian Cherabier, Johannes L. Schonberger, Martin R. Oswald, Marc Pollefeys, Andreas Geiger	We present a novel semantic 3D reconstruction framework which embeds variational regularization into a neural network.
570	The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking	Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, Qi Tian	In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges.
571	Learning with Biased Complementary Labels	Xiyu Yu, Tongliang Liu, Mingming Gong, Dacheng Tao	In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do extbf{not} belong to.
572	NAM: Non-Adversarial Unsupervised Domain Mapping	Yedid Hoshen, Lior Wolf	In this work, we introduce an alternative method: Non-Adversarial Mapping (NAM), which separates the task of target domain generative modeling from the cross-domain mapping task.
573	Motion Feature Network: Fixed Motion Filter for Action Recognition	Myunggi Lee, Seungeui Lee, Sungjoon Son, Gyutae Park, Nojun Kwak	In this paper, we propose MFNet (Motion Feature Network) containing motion blocks which make it possible to encode spatio-temporal information between adjacent frames in a unified network that can be trained end-to-end.
574	Transferable Adversarial Perturbations	Wen Zhou, Xin Hou, Yongjun Chen, Mengyun Tang, Xiangqi Huang, Xiang Gan, Yong Yang	In this paper, We propose a novel way of perturbations for adversarial examples to enable black-box transfer.
575	Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization	Thomas Holzmann, Michael Maurer, Friedrich Fraundorfer, Horst Bischof	We propose a method for urban 3D reconstruction, which incorporates semantic information and plane priors within the reconstruction process in order to generate visually appealing 3D models.
576	Learning Type-Aware Embeddings for Fashion Compatibility	Mariya I. Vasileva, Bryan A. Plummer, Krishna Dusad, Shreya Rajpal, Ranjitha Kumar, David Forsyth	This paper presents an approach to learning an image embedding that respects item type, and jointly learns notions of item similarity and compatibility in an end-to-end model.
577	Visual Reasoning with Multi-hop Feature Modulation	Florian Strub, Mathieu Seurin, Ethan Perez, Harm de Vries, Jeremie Mary, Philippe Preux, Aaron CourvilleOlivier Pietquin	visual dialogue task and matches state-of-the art on the ReferIt object retrieval task, and we provide additional qualitative analysis.
578	Object Detection in Video with Spatiotemporal Sampling Networks	Gedas Bertasius, Lorenzo Torresani, Jianbo Shi	We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos.
579	Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes	Yang He, Bernt Schiele, Mario Fritz	We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research.
580	Extreme Network Compression via Filter Group Approximation	Bo Peng, Wenming Tan, Zheyang Li, Shun Zhang, Di Xie, Shiliang Pu	In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation.
581	Efficient Sliding Window Computation for NN-Based Template Matching	Lior Talker, Yael Moses, Ilan Shimshoni	We there- fore propose in this paper an efficient NN-based algorithm.
582	MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models	Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy	This work introduces a new MAP-solver, based on the popular Dual Block-Coordinate Ascent principle.
583	Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model	Jie Guo, Zuojian Zhou, Limin Wang	We propose a sparse and low-rank reflection model for specular highlight detection and removal using a single input image.
584	ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera	Chao Li, Zheheng Zhao, Xiaohu Guo	This paper proposes a real-time dynamic scene reconstruction method capable of reproducing the motion, geometry, and segmentation simultaneously given live depth stream from a single RGB-D camera.
585	Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond	Piotr Koniusz, Yusuf Tas, Hongguang Zhang, Mehrtash Harandi, Fatih Porikli, Rui Zhang	We study an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC).
586	Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNN	Junho Jeon, Seungyong Lee	In this paper, we propose a pairwise depth image dataset generation method using dense 3D surface reconstruction with a filtering method to remove low quality pairs.
587	MRF Optimization with Separable Convex Prior on Partially Ordered Labels	Csaba Domokos, Frank R. Schmidt, Daniel Cremers	In this paper we propose a generalization to partially ordered sets.
588	Deep Generative Models for Weakly-Supervised Multi-Label Classification	Hong-Min Chu, Chih-Kuan Yeh, Yu-Chiang Frank Wang	In this paper, we tackle WS-MLC by learning deep generative models for describing the collected data.
589	Attend and Rectify: a gated attention mechanism for fine-grained recovery	Pau Rodriguez, Josep M. Gonfaus, Guillem Cucurull, F. XavierRoca, Jordi Gonzalez	We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition.
590	ADVIO: An Authentic Dataset for Visual-Inertial Odometry	Santiago Cortes, Arno Solin, Esa Rahtu, Juho Kannala	We take advantage of advances in pure inertial navigation, and develop a set of versatile and challenging real-world computer vision benchmark sets for visual-inertial odometry.
591	SRFeat: Single Image Super-Resolution with Feature Discrimination	Seong-Jin Park, Hyeongseok Son, Sunghyun Cho, Ki-Sang Hong, Seungyong Lee	In this paper, we propose a novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain.
592	Efficient 6-DoF Tracking of Handheld Objects from an Egocentric Viewpoint	Rohit Pandey, Pavel Pidlypenskyi, Shuoran Yang, Christine Kaeser-Chen	We tackle the problem of efficient 6-DoF tracking of a handheld controller from egocentric camera perspectives. We collected the HMD Controller dataset which consist of over 540,000 stereo image pairs labelled with the full 6-DoF pose of the handheld controller.
593	Learning Visual Question Answering by Bootstrapping Hard Attention	Mateusz Malinowski, Carl Doersch, Adam Santoro, Peter Battaglia	Here, we introduce a new approach for hard attention and find it achieves very competitive performance on a recently-released visual question answering dataset, equalling and in some cases surpassing similar soft attention architectures while entirely ignoring some features.
594	LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks	Dongqing Zhang, Jiaolong Yang, Dongqiangzi Ye, Gang Hua	To address this gap, we propose to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization.
595	Spatio-Temporal Channel Correlation Networks for Action Classification	Ali Diba, Mohsen Fayyaz, Vivek Sharma, M. Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool	The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)?
596	Video Summarization Using Fully Convolutional Sequence Networks	Mrigank Rochan, Linwei Ye, Yang Wang	In this paper, we formulate video summarization as a sequence labeling problem.
597	Deep Autoencoder for Combined Human Pose Estimation and Body Model Upscaling	Matthew Trumble, Andrew Gilbert, Adrian Hilton, John Collomosse	We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views.
598	A Style-Aware Content Loss for Real-time HD Style Transfer	Artsiom Sanakoyeu, Dmytro Kotovenko, Sabine Lang, Bjorn Ommer	To circumvent these issues, we propose a style-aware content loss, which is trained jointly with a deep encoder-decoder network for real-time, high-resolution stylization of images and videos.
599	A Zero-Shot Framework for Sketch based Image Retrieval	Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal	To circumvent this, we propose a generative approach for the SBIR task by proposing deep conditional generative models which take the sketch as an input and fill the missing information stochastically.
600	Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) Solver	Mikael Persson, Klas Nordberg	We present Lambda Twist; a novel P3P solver which is accurate, fast and robust.
601	Multi-modal Cycle-consistent Generalized Zero-Shot Learning	Rafael Felix, Vijay Kumar B. G., Ian Reid, Gustavo Carneiro	In this paper, we propose the use of such constraint based on a new regularization for the GAN training that forces the generated visual features to reconstruct their original semantic features.
602	Modeling Visual Context is Key to Augmenting Object Detection Datasets	Nikita Dvornik, Julien Mairal, Cordelia Schmid	In this work, we go one step further and leverage segmentation annotations to increase the number of object instances present on training data.
603	ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks	Qiang Qiu, Jose Lezama, Alex Bronstein, Guillermo Sapiro	In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests.
604	Extending Layered Models to 3D Motion	Dong Lao, Ganesh Sundaramoorthi	We consider the problem of inferring a layered representa-tion, its depth ordering and motion segmentation from a video in whichobjects may undergo 3D non-planar motion relative to the camera.
605	Scale-Awareness of Light Field Camera based Visual Odometry	Niclas Zeller, Franz Quint, Uwe Stilla	We propose a novel direct visual odometry algorithm for micro-lens-array-based light field cameras.
606	Joint 3D tracking of a deformable object in interaction with a hand	Aggeliki Tsoli, Antonis A. Argyros	We present a novel method that is able to track a complex deformable object in interaction with a hand.
607	Local Orthogonal-Group Testing	Ahmet Iscen, Ondrej Chum	Within the group testing framework we propose an efficient off-line construction of the search structures.
608	Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network	Qi Ye, Tae-Kyun Kim	In this paper, we tackle the self-occlusion issue and provide a complete description of observed poses given an input depth image by a novel method called hierarchical mixture density networks (HMDN).
609	Rolling Shutter Pose and Ego-motion Estimation using Shape-from-Template	Yizhen Lao, Omar Ait-Aider, Adrien Bartoli	Unlike all existing methods which perform 3D-2D registration after augmenting the Global Shutter (GS) projection model with the velocity parameters under various kinematic models, we propose to use local differential constraints.
610	Recognition in Terra Incognita	Sara Beery, Grant Van Horn, Pietro Perona	We present a dataset designed to measure recognition generalization to novel environments.
611	3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation	Angela Dai, Matthias Niessner	We present 3DMV, a novel method for 3D semantic scene segmentation of RGB-D scans using a joint 3D-multi-view prediction network.
612	A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines	Pedro Miraldo, Tiago Dias, Srikumar Ramalingam	We propose a minimal solution for pose estimation using both points and lines for a multi-perspective camera.
613	Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks	Miika Aittala, Fredo Durand	We propose a neural approach for fusing an arbitrary-length burst of photographs suffering from severe camera shake and noise into a sharp and noise-free image.
614	FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification	Xiaoqing Yin, Xinchao Wang, Jun Yu, Maojun Zhang, Pascal Fua, Dacheng Tao	In this paper, we propose an end-to-end multi-context collaborative deep network for removing distortions from single sheye images. To facilitate training, we construct a synthesized dataset that covers various scenes and distortion parameter settings.
615	Unveiling the Power of Deep Tracking	Goutam Bhat, Joakim Johnander, Martin Danelljan, Fahad Shahbaz Khan, Michael Felsberg	In this paper, we investigate this key issue and propose an approach to unlock the true potential of deep features for tracking.
616	LSQ++: Lower running time and higher recall in multi-codebook quantization	Julieta Martinez, Shobhit Zakhmi, Holger H. Hoos, James J. Little	Work in MCQ is heavily focused on lowering quantization error, thereby improving distance estimation and recall on benchmarks of visual descriptors at a fixed memory budget.
617	HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose Estimation	Yidan Zhou, Jian Lu, Kuo Du, Xiangbo Lin, Yi Sun, Xiaohong Ma	The goal of this paper is to estimate the 3D coordinates of the hand joints from a single depth image.
618	Retrospective Encoders for Video Summarization	Ke Zhang, Kristen Grauman, Fei Sha	In this paper, we propose a novel sequence-to-sequence learning model to address these deficiencies.
619	Sequential Clique Optimization for Video Object Segmentation	Yeong Jun Koh, Young-Yoon Lee, Chang-Su Kim	A novel algorithm to segment out objects in a video sequence is proposed in this work.
620	Constraint-Aware Deep Neural Network Compression	Changan Chen, Frederick Tung, Naveen Vedula, Greg Mori	We formulate the compression learning problem from the perspective of constrained Bayesian optimization, and introduce a cooling (annealing) strategy to guide the network compression towards the target constraints.
621	Linear RGB-D SLAM for Planar Environments	Pyojin Kim, Brian Coltin, H. Jin Kim	We propose a new formulation for including orthogonal planar features as a global model into a linear SLAM approach based on sequential Bayesian filtering.
622	Learning Region Features for Object Detection	Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, Jifeng Dai	This work proposes a general viewpoint that unifies existing region feature extraction methods and a novel method that is end-to-end learnable.
623	Video Compression through Image Interpolation	Chao-Yuan Wu, Nayan Singhal, Philipp Krahenbuhl	This paper presents an alternative in an end-to-end deep learning codec.
624	Key-Word-Aware Network for Referring Expression Image Segmentation	Hengcan Shi, Hongliang Li, Fanman Meng, Qingbo Wu	To address aforementioned issues, in this paper, we propose a key-word-aware network, which contains a query attention model and a key-word-aware visual context model.
625	LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction	Kai XU, Zhikang Zhang, Fengbo Ren	We propose a scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS images reconstruction.
626	Recurrent Fusion Network for Image captioning	Wenhao Jiang, Lin Ma, Yu-Gang Jiang, Wei Liu, Tong Zhang	In this paper, to exploit the complementary information from multiple encoders, we propose a novel recurrent fusion network (RFNet) for the image captioning task.
627	On Regularized Losses for Weakly-supervised CNN Segmentation	Meng Tang, Federico Perazzi, Abdelaziz Djelouah, Ismail Ben Ayed, Christopher Schroers, Yuri Boykov	This paper proposes and experimentally compares different losses integrating MRF/CRF regularization terms.
628	Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network	Yao Feng, Fan Wu, Xiaohu Shao, Yanfeng Wang, Xi Zhou	We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment.
629	A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI	Zhiwen Fan, Liyan Sun, Xinghao Ding, Yue Huang, Congbo Cai, John Paisley	In this paper, we proposed a segmentation-aware deep fusion network called SADFN for compressed sensing MRI.
630	End-to-End Deep Structured Models for Drawing Crosswalks	Justin Liang, Raquel Urtasun	In this paper we address the problem of detecting crosswalks from LiDAR and camera imagery.
631	Few-Shot Human Motion Prediction via Meta-Learning	Liang-Yan Gui, Yu-Xiong Wang, Deva Ramanan, Jose M. F. Moura	To accomplish this, we propose proactive and adaptive meta-learning (PAML) that introduces a novel combination of model-agnostic meta-learning and model regression networks and unifies them into an integrated, end-to-end framework.
632	Correcting the Triplet Selection Bias for Triplet Loss	Baosheng Yu, Tongliang Liu, Mingming Gong, Changxing Ding, Dacheng Tao	In this paper, we propose a new variant of triplet loss, which tries to reduce the bias in triplet sampling by adaptively correcting the distribution shift on sampled triplets.
633	3D Face Reconstruction from Light Field Images: A Model-free Approach	Mingtao Feng, Syed Zulqarnain Gilani, Yaonan Wang, Ajmal Mian	In this paper, we exploit the Epipolar Plane Images (EPI) obtained from light field cameras and learn CNN models that recover horizontal and vertical 3D facial curves from the respective horizontal and vertical EPIs.
634	Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering	Medhini Narasimhan, Alexander G. Schwing	To address this issue, we develop a learning-based approach which goes straight to the facts via a learned embedding space.
635	Sidekick Policy Learning for Active Visual Exploration	Santhosh K. Ramakrishnan, Kristen Grauman	We introduce sidekick policy learning to capitalize on this imbalance of observability.
636	Good Line Cutting: towards Accurate Pose Tracking of Line-assisted VO/VSLAM	Yipu Zhao, Patricio A. Vela	The solution we present is good line cutting, which extracts the most-informative sub-segment from each 3D line for use within the pose optimization formulation.
637	Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds	Haroon Idrees, Muhmmad Tayyab, Kishan Athrey, Dong Zhang, Somaya Al-Maadeed, Nasir Rajpoot, Mubarak Shah	In this paper, we propose a novel approach that simultaneously solves the problems of counting, density map estimation and localization of people in a given dense crowd image. Since localization requires high-quality images and annotations, we introduce UCF-QNRF dataset that overcomes the shortcomings of previous datasets, and contains 1.25 million humans manually marked with dot annotations.
638	Attentive Semantic Alignment with Offset-Aware Correlation Kernels	Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho	In this paper, we introduce an attentive semantic alignment method that focuses on reliable correlations, filtering out distractors.
639	“Factual” or “Emotional”: Stylized Image Captioning with Adaptive Learning and Attention	Tianlang Chen, Zhongping Zhang, Quanzeng You, Chen Fang, Zhaowen Wang, Hailin Jin, Jiebo Luo	In this paper, we propose a novel stylized image captioning model that effectively takes both requirements into consideration.
640	CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping	Haitian Zheng, Mengqi Ji, Haoqian Wang, Yebin Liu, Lu Fang	To resolve these issues, we present CrossNet, an end-to-end and fully-convolutional deep neural network using cross-scale warping.
641	CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps	Paul Hongsuck Seo, Tobias Weyand, Jack Sim, Bohyung Han	To tackle this issue, we propose a simple but effective algorithm, combinatorial partitioning, which generates a large number of fine-grained output classes by intersecting multiple coarse-grained partitionings of the earth.
642	Single Image Water Hazard Detection using FCN with Reflection Attention Units	Xiaofeng Han, Chuong Nguyen, Shaodi You, Jianfeng Lu	In this paper, we present a water puddle detection method based on a Fully Convolutional Network (FCN) with our newly proposed Reflection Attention Units (RAUs).
643	ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation	Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, Hannaneh Hajishirzi	We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints.
644	Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition	Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding	In this paper, we propose a novel attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images.
645	Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection	Lei Zhu, Zijun Deng, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, Pheng-Ann Heng	This paper presents a network to detect shadows by exploring and combining global context in deep layers and local context in shallow layers of a deep convolutional neural network (CNN).
646	Where are the blobs: Counting by Localization with Point Supervision	Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro, David Vazquez, Mark Schmidt	Our contributions are three-fold: (1) we propose a novel loss function that encourages the network to output a single blob per object instance using point-level annotations only; (2) we design two methods for splitting large predicted blobs between object instances; and (3) we show that our method achieves new state-of-the-art results on several challenging datasets including the Pascal VOC and the Penguins dataset.
647	Dense Semantic and Topological Correspondence of 3D Faces without Landmarks	Zhenfeng Fan, Xiyuan Hu, Chen Chen, Silong Peng	We propose a general framework for dense correspondence of 3D faces without landmarks in this paper.
648	Textual Explanations for Self-Driving Vehicles	Jinkyu Kim, Anna Rohrbach, Trevor Darrell, John Canny, Zeynep Akata	We propose a new approach to introspective explanations which consists of two parts.
649	Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification	Cheng Wang, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang	We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
650	Efficient Relative Attribute Learning using Graph Neural Networks	Zihang Meng, Nagesh Adluru, Hyunwoo J. Kim, Glenn Fung, Vikas Singh	In this paper, we show how emerging ideas in graph neural networks can yield a unified solution to various problems that broadly fall under relative attribute learning.
651	Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias	Rameswar Panda, Jianming Zhang, Haoxiang Li, Joon-Young Lee, Xin Lu, Amit K. Roy-Chowdhury	Based on our analysis, we propose a webly supervised approach by leveraging a large quantity of stock image data.
652	Joint & Progressive Learning from High-Dimensional Data for Multi-Label Classification	Danfeng Hong, Naoto Yokoya, Jian Xu, Xiaoxiang Zhu	Despite the fact that nonlinear subspace learning techniques (e.g. manifold learning) have successfully applied to data representation, there is still room for improvement in explainability (explicit mapping), generalization (out-of-samples), and cost-effectiveness (linearization).
653	Using Object Information for Spotting Text	Shitala Prasad, Adams Wai Kin Kong	In this paper, a text spotting algorithm based on text and object dependency is proposed.
654	MVTec D2S: Densely Segmented Supermarket Dataset	Patrick Follmann, Tobias Bottger, Philipp Hartinger, Rebecca Konig, Markus Ulrich	We introduce the Densely Segmented Supermarket (D2S) dataset, a novel benchmark for instance-aware semantic segmentation in an industrial domain.
655	Video Object Detection with an Aligned Spatial-Temporal Memory	Fanyi Xiao, Yong Jae Lee	We introduce Spatial-Temporal Memory Networks for video object detection.
656	Asynchronous, Photometric Feature Tracking using Events and Frames	Daniel Gehrig, Henri Rebecq, Guillermo Gallego, Davide Scaramuzza	We present a method that leverages the complementarity of event cameras and standard cameras to track visual features with low-latency.
657	Deep Recursive HDRI: Inverse Tone Mapping using Generative Adversarial Networks	Siyeong Lee, Gwon Hwan An, Suk-Ju Kang	We propose a novel method for restoring the lost dynamic range from a single low dynamic range image through a deep neural network.
658	DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition	Melih Engin, Lei Wang, Luping Zhou, Xinwang Liu	More importantly, we introduce the {Daleckiv{i}-Krev{i}n formula} from Operator theory to give a concise and unified result on differentiating general functions defined on symmetric positive-definite (SPD) matrix, which shows its better numerical stability in conducting backpropagation compared with the existing method when handling the Riemannian geometry of SPD matrix.
659	Remote Photoplethysmography Correspondence Feature for 3D Mask Face Presentation Attack Detection	Si-Qi Liu, Xiangyuan Lan, Pong C. Yuen	In this paper, we propose a new liveness feature, called rPPG correspondence feature (CFrPPG) to precisely identify the heartbeat vestige from the observed noisy rPPG signals.
660	Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular Clues	Henry Wing Fung Yeung, Junhui Hou, Jie Chen, Yuk Ying Chung, Xiaoming Chen	In this paper, we propose a learning based algorithm to reconstruct a densely-sampled LF fast and accurately from a sparsely-sampled LF in one forward pass.
661	Deep Discriminative Model for Video Classification	Mohammad Tavakolian, Abdenour Hadid	This paper presents a new deep learning approach for video-based scene classification.
662	Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image	Zhengqin Li, Kalyan Sunkavalli, Manmohan Chandraker	We propose a material acquisition system that can recover the spatially-varying BRDF and normal map of a near-planar surface from a single image captured by a handheld mobile phone camera.
663	Image Reassembly Combining Deep Learning and Shortest Path Problem	Marie-Morgane Paumard, David Picard, Hedi Tabia	The main contributions of this work are: 1) several deep neural architectures to predict the relative position of image fragments that outperform the previous state of the art; 2) casting the reassembly problem into the shortest path in a graph problem for which we provide several construction algorithms depending on available information; 3) a new dataset of images taken from the Metropolitan Museum of Art (MET) dedicated to image reassembly for which we provide a clear setup and a strong baseline.
664	Coded Illumination and Imaging for Fluorescence Based Classification	Yuta Asano, Misaki Meguro, Chao Wang, Antony Lam, Yinqiang Zheng, Takahiro Okabe, Imari Sato	In this paper, we propose a coded illumination approach whereby light spectra are learned such that key visual fluorescent features can be easily seen for material classification.
665	GANimation: Anatomically-aware Facial Animation from a Single Image	Albert Pumarola, Antonio Agudo, Aleix M. Martinez, Alberto Sanfeliu, Francesc Moreno-Noguer	To address this limitation, in this paper, we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression.
666	Deep Kalman Filtering Network for Video Compression Artifact Reduction	Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Zhiyong Gao, Ming-Ting Sun	In this paper, we model the video artifact reduction task as a Kalman filtering procedure and restore decoded frames through a deep Kalman filtering network.
667	A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment	Roberto Valle, Jose M. Buenaposada, Antonio Valdes, Luis Baumela	In this paper we present DCFE, a real-time facial landmark regression method based on a coarse-to-fine Ensemble of Regression Trees (ERT).
668	Deep Expander Networks: Efficient Deep Networks from Graph Theory	Ameya Prabhu, Girish Varma, Anoop Namboodiri	Inspired by these techniques, we propose to model connections between filters of a CNN using graphs which are simultaneously sparse and well connected.
669	Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation	Hyojin Bahng, Seungjoo Yoo, Wonwoong Cho, David Keetae Park, Ziming Wu, Xiaojuan Ma, Jaegul Choo	This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette. For this task, we introduce our manually curated dataset called Palette-and-Text (PAT).
670	BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization	Yue Wu, Wael Abd-Almageed, Prem Natarajan	We introduce a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet.
671	Task-Aware Image Downscaling	Heewon Kim, Myungsub Choi, Bee Lim, Kyoung Mu Lee	In this paper, we present a novel operation called task-aware image downscaling to support an upscaling task.
672	Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition	Chaojian Yu, Xinyi Zhao, Qi Zheng, Peng Zhang, Xinge You	In this paper, we present a novel model to address these issues.
673	Self-Calibration of Cameras with Euclidean Image Plane in Case of Two Views and Known Relative Rotation Angle	Evgeniy Martyushev	In this paper, we propose a non-iterative self-calibration algorithm for a camera with Euclidean image plane in case the remaining three internal parameters — the focal length and the principal point coordinates — are fixed but unknown.
674	To learn image super-resolution, use a GAN to learn how to do image degradation first	Adrian Bulat, Jing Yang, Georgios Tzimiropoulos	To circumvent this problem, we propose a two-stage process which firstly trains a High-to-Low Generative Adversarial Network (GAN) to learn how to degrade and downsample high-resolution images requiring, during training, only extit{unpaired} high and low-resolution images.
675	Multi-scale Residual Network for Image Super-Resolution	Juncheng Li, Faming Fang, Kangfu Mei, Guixu Zhang	In this paper, we propose a novel multi-scale residual network (MSRN) to fully exploit the image features, which outperform most of the state-of-the-art methods.
676	Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search	Yinlong Liu, Chen Wang, Zhijian Song, Manning Wang	In this paper, we decouple the optimization of translation and rotation, and we propose a fast BnB algorithm to globally optimize the 3D translation parameter first.
677	FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans	Chen Liu, Jiaye Wu, Yasutaka Furukawa	The ultimate goal of this indoor mapping research is to automatically reconstruct a floorplan simply by walking through a house with a smartphone in a pocket. We have created a benchmark for floorplan reconstruction by acquiring RGBD video streams for 155 residential houses or apartments with Google Tango phones and annotating complete floorplan information.
678	Facial Dynamics Interpreter Network: What are the Important Relations between Local Dynamics for Facial Trait Estimation?	Seong Tae Kim, Yong Man Ro	In this paper, a novel deep learning approach has been proposed to interpret the important relations between local dynamics for estimating facial traits from expression sequence.
679	Transferring GANs: generating images from limited data	Yaxing Wang, Chenshen Wu, Luis Herranz, Joost van de Weijer, Abel Gonzalez-Garcia, Bogdan Raducanu	Therefore, we study domain adaptation applied to image generation with generative adversarial networks.
680	A Dataset for Lane Instance Segmentation in Urban Environments	Brook Roberts, Sebastian Kaltwang, Sina Samangooei, Mark Pender-Bare, Konstantinos Tertikas, John Redford	Therefore, we propose a semi-automated method that allows for efficient labelling of image sequences by utilising an estimated road plane in 3D based on where the car has driven and projecting labels from this plane into all images of the sequence. We are releasing a dataset of 24,000 images and additionally show experimental semantic segmentation and instance segmentation results.
681	Visual Question Generation for Class Acquisition of Unknown Objects	Kohei Uehara, Antonio Tejero-De-Pablos, Yoshitaka Ushiku, Tatsuya Harada	In this paper, we propose a method for generating questions about unknown objects in an image, as means to get information about classes that have not been learned.
682	DeepVS: A Deep Learning Based Video Saliency Prediction Approach	Lai Jiang, Mai Xu, Tie Liu, Minglang Qiao, Zulin Wang	In this paper, we propose a novel deep learning based video saliency prediction method, named DeepVS.
683	Saliency Preservation in Low-Resolution Grayscale Images	Shivanthan Yohanandan, Andy Song, Adrian G. Dyer, Dacheng Tao	In this study, we explain the biological and computational motivation for LG, and show, through a range of human eye-tracking and computational modeling experiments, that saliency information is preserved in LG images.
684	Pairwise Relational Networks for Face Recognition	Bong-Nam Kang, Yonghyun Kim, Daijin Kim	To investigate the effective features for face recognition, we propose a novel face recognition method, called a pairwise relational network (PRN), that obtains local appearance patches around landmark points on the feature map, and captures the pairwise relation between a pair of local appearance patches.
685	Proxy Clouds for Live RGB-D Stream Processing and Consolidation	Adrien Kaiser, Jose Alonso Ybanez Zepeda, Tamy Boubekeur	We propose a new multiplanar superstructure for unified real-time processing of RGB-D data.
686	U-PC: Unsupervised Planogram Compliance	Archan Ray, Nishant Kumar, Avishek Shaw, Dipti Prasad Mukherjee	We present an end-to-end solution for recognizing merchandise displayed in the shelves of a supermarket.
687	Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World	Matteo Fabbri, Fabio Lanzi, Simone Calderara, Andrea Palazzi, Roberto Vezzani, Rita Cucchiara	For the purpose, we propose a deep network architecture that jointly extracts people body parts and associates them across short temporal spans. To overcome the lack of surveillance data with tracking, body part and occlusion annotations we created the vastest Computer Graphics dataset for people tracking in urban scenarios by exploiting a photorealistic videogame.
688	Deep Metric Learning with Hierarchical Triplet Loss	Weifeng Ge	We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information.
689	Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields	Kejie Li, Trung Pham, Huangying Zhan, Ian Reid	We propose a novel approach that addresses this limitation by replacing masks with ”deformation-fields”.
690	DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation	Bharath Bhushan Damodaran, Benjamin Kellenberger, Remi Flamary, Devis Tuia, Nicolas Courty	In this work we explore a solution, named DeepJDOT, to tackle this problem: through a measure of discrepancy on joint deep representations/labels based on optimal transport, we not only learn new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier.
691	Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization	Daniel Jakubovitz, Raja Giryes	In this work, we suggest a theoretically inspired novel approach to improve the networks’ robustness.
692	Joint Learning of Intrinsic Images and Semantic Segmentation	Anil S. Baslamisli, Thomas T. Groenestege, Partha Das, Hoang-An Le, Sezer Karaoglu, Theo Gevers	Therefore, in this paper, the tasks of semantic segmentation and intrinsic image decomposition are considered as a combined process by exploring their mutual relationship in a joint fashion.
693	Recurrent Tubelet Proposal and Recognition Networks for Action Detection	Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao, Tao Mei	Specifically, we present a novel deep architecture called Recurrent Tubelet Proposal and Recognition (RTPR) networks to incorporate temporal context for action detection.
694	Domain transfer through deep activation matching	Haoshuo Huang, Qixing Huang, Philipp Krahenbuhl	We introduce a layer-wise unsupervised domain adaptation approach for the task of semantic segmentation.
695	Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study	Zhenyu Wu, Zhangyang Wang, Zhaowen Wang, Hailin Jin	This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework.
696	Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera	Timo von Marcard, Roberto Henschel, Michael J. Black, Bodo Rosenhahn, Gerard Pons-Moll	In this work, we propose a method that combines a single hand-held camera and a set of Inertial Measurement Units (IMUs) attached at the body limbs to estimate accurate 3D poses in the wild.
697	Beyond local reasoning for stereo confidence estimation with deep learning	Fabio Tosi, Matteo Poggi, Antonio Benincasa, Stefano Mattoccia	Therefore, in this paper, we propose to exploit nearby and farther clues available from image and disparity domains to obtain a more accurate confidence estimation.
698	Self-supervised Knowledge Distillation Using Singular Value Decomposition	Seung Hyun Lee, Dae Ha Kim, Byung Cheol Song	To improve the quality of the transferred knowledge from T-DNN, we propose a new knowledge distillation using singular value decomposition (SVD).
699	Implicit 3D Orientation Learning for 6D Object Detection from RGB Images	Martin Sundermeyer, Zoltan-Csaba Marton, Maximilian Durner, Manuel Brucker, Rudolph Triebel	We propose a real-time RGB-based pipeline for object detection and 6D pose estimation.
700	Concept Mask: Large-Scale Segmentation from Semantic Concepts	Yufei Wang, Zhe Lin, Xiaohui Shen, Jianming Zhang, Scott Cohen	We formulate semantic segmentation as a problem of image segmentation given a semantic concept, and propose a novel system which can potentially handle an unlimited number of concepts, including objects, parts, stuff, and attributes.
701	Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net	Xingang Pan, Ping Luo, Jianping Shi, Xiaoou Tang	Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we present IBN-Net, a novel convolutional architecture, which remarkably enhances a CNN’s modeling ability on one domain (e.g. Cityscapes) as well as its generalization capacity on another domain (e.g. GTA5) without finetuning.
702	Adaptively Transforming Graph Matching	Fudong Wang, Nan Xue, Yipeng Zhang, Xiang Bai, Gui-Song Xia	In this paper, we introduce an adaptively transforming graph matching (ATGM) method from the perspective of functional representation.
703	Deep Continuous Fusion for Multi-Sensor 3D Object Detection	Ming Liang, Bin Yang, Shenlong Wang, Raquel Urtasun	In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization.
704	PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence	Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn	This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images.
705	Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing	Armand Zampieri, Guillaume Charpiat, Nicolas Girard, Yuliya Tarabalka	We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging.
706	Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)	Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, Shengjin Wang	Instead of using external resources like pose estimator, we consider content consistency within each part for precise part location.
707	Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers	Apoorv Vyas, Nataraj Jammalamadaka, Xia Zhu, Dipankar Das, Bharat Kaul, Theodore L. Willke	In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers.
708	Start, Follow, Read: End-to-End Full-Page Handwriting Recognition	Curtis Wigington, Chris Tensmeyer, Brian Davis, William Barrett, Brian Price, Scott Cohen	Motivated by this, we present a deep learning model that jointly learns text detection, segmentation, and recognition using mostly images without detection or segmentation annotations.
709	PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities	Lan Wang, Chenqiang Gao, Luyu Yang, Yue Zhao, Wangmeng Zuo, Deyu Meng	In this paper, we propose a novel Partial-modal Generative Adversarial Networks (PM-GANs) that learns a full-modal representation using data from only partial modalities.
710	Adversarial Geometry-Aware Human Motion Prediction	Liang-Yan Gui, Yu-Xiong Wang, Xiaodan Liang, Jose M. F. Moura	Specifically, rather than using the conventional Euclidean loss, we propose a novel frame-wise geodesic loss as a geometrically meaningful, more precise distance measurement.
711	WildDash – Creating Hazard-Aware Benchmarks	Oliver Zendel, Katrin Honauer, Markus Murschitz, Daniel Steininger, Gustavo Fernandez Dominguez	In this work, we present a new test dataset for semantic and instance segmentation for the automotive domain.
712	RefocusGAN: Scene Refocusing using a Single Image	Parikshit Sakurikar, Ishit Mehta, Vineeth N. Balasubramanian, P. J. Narayanan	We introduce RefocusGAN, a deblur-then-reblur approach to single image refocusing.
713	Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving	Peiliang Li, Tong Qin, andShaojie Shen	We propose a stereo vision-based approach for tracking the camera ego-motion and 3D semantic objects in dynamic autonomous driving scenarios.
714	Zero-shot keyword spotting for visual speech recognition in-the-wild	Themos Stafylakis, Georgios Tzimiropoulos	Different to prior works on KWS, which try to learn word representations merely from sequences of graphemes (i.e. letters), we propose the use of a grapheme-to-phoneme encoder-decoder model which learns how to map words to their pronunciation.
715	Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting	Wei Liu, Shengcai Liao, Weidong Hu, Xuezhi Liang, Xiao Chen	Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting
716	Generative Adversarial Network with Spatial Attention for Face Attribute Editing	Gang Zhang, Meina Kan, Shiguang Shan, Xilin Chen	Therefore, we introduce the spatial attention mechanism into GAN framework (referred to as SaGAN), to only alter the attribute-specific region and keep the rest unchanged.
717	Scenes-Objects-Actions: A Multi-Task, Multi-Label Video Dataset	Jamie Ray, Heng Wang, Du Tran, Yufei Wang, Matt Feiszli, Lorenzo Torresani, Manohar Paluri	This paper introduces a large-scale, multi-label and multitask video dataset named Scenes-Objects-Actions (SOA).
718	Descending, lifting or smoothing: Secrets of robust cost optimization	Christopher Zach, Guillaume Bourmaud	In this work we identify three classes of deterministic second-order algorithms that are able to tackle this type of optimization problem: direct approaches that aim to optimize the robust cost directly with a second order method, lifting-based approaches that add so called lifting variables to embed the given robust cost function into a higher dimensional space, and graduated optimization methods that solve a sequence of smoothed cost functions.
719	Deep Bilevel Learning	Simon Jenni, Paolo Favaro	We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent.
720	Realtime Time Synchronized Event-based Stereo	Alex Zihao Zhu, Yibo Chen, Kostas Daniilidis	In this work, we propose a novel event based stereo method which addresses the problem of motion blur for a moving event camera.
721	Understanding Perceptual and Conceptual Fluency at a Large Scale	Shengli Hu, Ali Borji	We propose and provide estimation methods based on training DCNNs to extract and evaluate two independent constructs for designs: perceptual distinctiveness (“perceptual fluency” metrics) and ambiguity in meaning (“conceptual fluency” metrics) of each logo. We create a dataset of 543,758 logo designs spanning 39 industrial categories and 216 countries.
722	Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation	Daniel Maurer, Nico Marniok, Bastian Goldluecke, Andres Bruhn	In the present paper, we tackle this problem.
723	Unsupervised Learning of Multi-Frame Optical Flow with Occlusions	Joel Janai, Fatma Guney, Anurag Ranjan, Michael Black, Andreas Geiger	In this paper, we propose a framework for unsupervised learning of optical flow and occlusions over multiple frames.
724	Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images	Keisuke Tateno, Nassir Navab, Federico Tombari	To fill this gap, we propose a learning approach for panoramic depth map estimation from a single image.
725	Accelerating Dynamic Programs via Nested Benders Decomposition with Application to Multi-Person Pose Estimation	Shaofei Wang, Alexander Ihler, Konrad Kording, Julian Yarkony	We present a novel approach to solve dynamic programs (DP), which are frequent in computer vision, on tree-structured graphs with exponential node state space.
726	OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas	Nikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas, Petros Daras	In this work, we circumvent the challenges associated with acquiring high quality 360 datasets with ground truth depth annotations, by re-using recently released large scale 3D datasets and re-purposing them to 360 via rendering.
727	Joint optimization for compressive video sensing and reconstruction under hardware constraints	Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara	In this paper, we propose a method of jointly optimizing the exposure patterns of compressive sensing and the reconstruction framework under hardware constraints.
728	A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation	Hieu Le, Tomas F. Yago Vicente, Vu Nguyen, Minh Hoai, Dimitris Samaras	We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples.
729	Simple Baselines for Human Pose Estimation and Tracking	Bin Xiao, Haiping Wu, Yichen Wei	This work provides simple and effective baseline methods.
730	Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance	Zhixin Shu, Mihir Sahasrabudhe, Riza Alp Guler, Dimitris Samaras, Nikos Paragios, Iasonas Kokkinos	In this work we introduce the Deforming Autoencoder, a generative model for images that disentangles shape from appearance in a latent representation space that is learned in a fully unsupervised manner.
731	Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification	Eric Muller-Budack, Kader Pustu-Iren, Ralph Ewerth	In this paper, we introduce several deep learning methods, which pursue the latter approach and treat geolocalization as a classification problem where the earth is subdivided into geographical cells.
732	Universal Sketch Perceptual Grouping	Ke Li, Kaiyue Pang, Jifei Song, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Honggang Zhang	In this work we aim to develop a universal sketch grouper.
733	License Plate Detection and Recognition in Unconstrained Scenarios	Sergio Montazzolli Silva, Claudio Rosito Jung	This work proposes a complete ALPR system focusing on unconstrained capture scenarios, where the LP might be considerably distorted due to oblique views.
734	Affine Correspondences between Central Cameras for Rapid Relative Pose Estimation	Ivan Eichhardt, Dmitry Chetverikov	This paper presents a novel algorithm to estimate the relative pose, i.e. the 3D rotation and translation of two cameras, from two affine correspondences (ACs) considering any central camera model.
735	ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases	Pierre Stock, Moustapha Cisse	The contribution of this study is threefold.
736	Human Motion Analysis with Deep Metric Learning	Huseyin Coskun, David Joseph Tan, Sailesh Conjeti, Nassir Navab, Federico Tombari	Specifically, we propose (1) a novel metric learning objective based on a triplet architecture and Maximum Mean Discrepancy; as well as, (2) a novel deep architecture based on attentive recurrent neural networks.
737	Real-to-Virtual Domain Unification for End-to-End Autonomous Driving	Luona Yang, Xiaodan Liang, Tairui Wang, Eric Xing	In this work, we address the above limitations by taking advantage of virtual data collected from driving simulators, and present DU-drive, an unsupervised real-to-virtual domain unification framework for end-to-end autonomous driving.
738	Imagine This! Scripts to Compositions to Videos	Tanmay Gupta, Dustin Schwenk, Ali Farhadi, Derek Hoiem, Aniruddha Kembhavi	As a step towards this goal, we present the Composition Retrieval and Fusion Networks (CRAFT), a model capable of learning this knowledge from video-caption data and applying it for generating videos from novel captions.
739	Exploring Visual Relationship for Image Captioning	Ting Yao, Yingwei Pan, Yehao Li, Tao Mei	In this paper, we introduce a new design to explore the connections between objects for image captioning under the umbrella of attention-based encoder-decoder framework.
740	ExplainGAN: Model Explanation via Decision Boundary Crossing Transformations	Pouya Samangouei, Ardavan Saeedi, Liam Nakagawa, Nathan Silberman	We introduce a new method for interpreting computer vision models: visually perceptible, decision-boundary crossing transformations.
741	RESOUND: Towards Action Recognition without Representation Bias	Yingwei Li, Yi Li, Nuno Vasconcelos	RESOUND: Towards Action Recognition without Representation Bias
742	Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction	Michal Polic, Wolfgang Forstner, Tomas Pajdla	We present a new algorithm which employs the sparsity of the uncertainty propagation and speeds the computation up about ten times wrt previous approaches.
743	Deep Randomized Ensembles for Metric Learning	Hong Xuan, Richard Souvenir, Robert Pless	In this work, we propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results.
744	The Mutex Watershed: Efficient, Parameter-Free Image Partitioning	Steffen Wolf, Constantin Pape, Alberto Bailoni, Nasim Rahaman, Anna Kreshuk, Ullrich Kothe, FredA. Hamprecht	Here, we propose an algorithm with empirically linearithmic complexity.
745	Integral Human Pose Regression	Xiao Sun, Bin Xiao, Fangyin Wei, Shuang Liang, Yichen Wei	This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues.
746	Quadtree Convolutional Neural Networks	Pradeep Kumar Jayaraman, Jianhan Mei, Jianfei Cai, Jianmin Zheng	This paper presents a Quadtree Convolutional Neural Network (QCNN) for efficiently learning from image datasets representing sparse data such as handwriting, pen strokes, freehand sketches, etc.
747	Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data	Tian Feng, Quang-Trung Truong, Duc Thanh Nguyen, Jing Yu Koh, Lap-Fai Yu, Alexander Binder, Sai-Kit Yeung	This paper proposes a method for automatic urban zoning using higher-order Markov random fields (HO-MRF) built on multi-view imagery data including street-view photos and top-view satellite images.
748	Self-produced Guidance for Weakly-supervised Object Localization	Xiaolin Zhang, Yunchao Wei, Guoliang Kang, Yi Yang, Thomas Huang	We propose to generate Self-produced Guidance (SPG) masks which separate the foreground, the object of interest, from the background to provide the classification networks with spatial correlation information of pixels.
749	ECO: Efficient Convolutional Network for Online Video Understanding	Mohammadreza Zolfaghari, Kamaljeet Singh, Thomas Brox	In this paper, we introduce a network architecture that takes long-term content into account and enables fast per-video processing at the same time.
750	Multi-Scale Structure-Aware Network for Human Pose Estimation	Lipeng Ke, Ming-Ching Chang, Honggang Qi, Siwei Lyu	Our method can effectively improve state-of-the-art pose estimation methods that suffer from difficulties in scale varieties, occlusions, and complex multi-person scenarios.
751	Does Haze Removal Help CNN-based Image Classification?	Yanting Pei, Yaping Huang, Qi Zou, Yuhang Lu, Song Wang	In this paper, we empirically study this problem in the important task of image classification by using both synthetic and real hazy image datasets.
752	Quaternion Convolutional Neural Networks	Xuanyu Zhu, Yi Xu, Hongteng Xu, Changjian Chen	Focusing on color images, which can be naturally represented as quaternion matrices, we propose a quaternion convolutional neural network (QCNN) model to obtain more representative features.
753	Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation	Eddy Ilg, Tonmoy Saikia, Margret Keuper, Thomas Brox	In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with optical flow or disparities.
754	Single Shot Scene Text Retrieval	Lluis Gomez, Andres Mafla, Marcal Rusinol, Dimosthenis Karatzas	In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text.
755	Learning to Predict Crisp Boundaries	Ruoxi Deng, Chunhua Shen, Shengjun Liu, Huibing Wang, Xinru Liu	In this work, the aim is to make CNNs produce sharp boundaries without post-processing.
756	Diverse and Coherent Paragraph Generation from Images	Moitreya Chatterjee, Alexander G. Schwing	To address those challenges, we propose to augment paragraph generation techniques with “coherence vectors,” “global topic vectors,” and modeling of the inherent ambiguity of associating paragraphs with images, via a variational auto-encoder formulation.
757	Folded Recurrent Neural Networks for Future Video Prediction	Marc Oliu, Javier Selva, Sergio Escalera	This work introduces double-mapping Gated Recurrent Units (dGRU), an extension of standard GRUs where the input is considered as a recurrent state.
758	Image Manipulation with Perceptual Discriminators	Diana Sungatullina, Egor Zakharov, Dmitry Ulyanov, Victor Lempitsky	In this work, we show how these two ideas can be combined in a principled and non-additive manner for unaligned image translation tasks.
759	DeepTAM: Deep Tracking and Mapping	Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox	We present a system for keyframe-based dense camera tracking and depth map estimation that is entirely learned.
760	W-TALC: Weakly-supervised Temporal Activity Localization and Classification	Sujoy Paul, Sourya Roy, Amit K. Roy-Chowdhury	Towards this goal, we present W-TALC, a Weakly-supervised Temporal Activity Localization and Classification framework using only video-level labels.
761	Is Robustness the Cost of Accuracy? — A Comprehensive Study on the Robustness of 18 Deep Image Classification Models	Dong Su, Huan Zhang, Hongge Chen, Jinfeng Yi, Pin-Yu Chen, Yupeng Gao	To demystify the trade-offs between robustness and accuracy, in this paper we thoroughly benchmark 18 ImageNet models using multiple robustness metrics, including the distortion, success rate and transferability of adversarial examples between 306 pairs of models.
762	3D Ego-Pose Estimation via Imitation Learning	Ye Yuan, Kris Kitani	Motivated by this, we propose a novel control-based approach to model human motion with physics simulation and use imitation learning to learn a video-conditioned control policy for ego-pose estimation.
763	Supervising the new with the old: learning SFM from SFM	Maria Klodt, Andrea Vedaldi	In this paper, we propose a number of improvements to these approaches.
764	Towards Realistic Predictors	Pei Wang, Nuno Vasconcelos	In this paper, we talk about a particular case of it, realistic classifiers.
765	Value-aware Quantization for Training and Inference of Neural Networks	Eunhyeok Park, Sungjoo Yoo, Peter Vajda	We present new techniques to apply the proposed quantization to training and inference.
766	Structural Consistency and Controllability for Diverse Colorization	Safa Messaoud, David Forsyth, Alexander G. Schwing	To address this issue, we develop a conditional random field based variational auto-encoder formulation which is able to achieve diversity while taking into account structural consistency.
767	A Dataset and Architecture for Visual Reasoning with a Working Memory	Guangyu Robert Yang, Igor Ganichev, Xiao-Jing Wang, Jonathon Shlens, David Sussillo	Preliminary analyses of the network architectures trained on COG demonstrate that the network accomplishes the task in a manner interpretable to humans. Inspired by a rich tradition of visual reasoning and memory in cognitive psychology and neuroscience, we developed an artificial, configurable visual question and answer dataset (COG) to parallel experiments in humans and animals.
768	From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data	Daniel Coelho de Castro, Sebastian Nowozin	We propose an integrated Bayesian model that coherently reasons about the observed images, identities, partial knowledge about names, and the situational context of each observation.
769	Open Set Learning with Counterfactual Images	Lawrence Neal, Matthew Olson, Xiaoli Fern, Weng-Keen Wong, Fuxin Li	To detect unknown classes while still generalizing to new instances of existing classes, we introduce a dataset augmentation technique that we call counterfactual image generation.
770	Fully-Convolutional Point Networks for Large-Scale Point Clouds	Dario Rethage, Johanna Wald, Jurgen Sturm, Nassir Navab, Federico Tombari	This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data.
771	Improving Shape Deformation in Unsupervised Image-to-Image Translation	Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin	Inspired by semantic segmentation, we introduce a discriminator with dilated convo- lutions which is able to use information from across the entire image to train a more context-aware generator.
772	SwapNet: Garment Transfer in Single View Images	Amit Raj, Patsorn Sangkloy, Huiwen Chang, Jingwan Lu, Duygu Ceylan, James Hays	We present SwapNet, a framework to transfer garments across images of people with arbitrary body pose, shape, and clothing.
773	Learning SO(3) Equivariant Representations with Spherical CNNs	Carlos Esteves, Christine Allen-Blanchette, Ameesh Makadia, Kostas Daniilidis	We model 3D data with multi-valued spherical functions and we propose a novel spherical convolutional network that implements exact convolutions on the sphere by realizing them in the spherical harmonic domain.
774	Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular video	Ernesto Brau, Jinyan Guan, Tanya Jeffries, Kobus Barnard	We provide a Bayesian generative model for the temporal scene that captures the joint probability of camera parameters, locations of people, their gaze, what they are looking at, and locations of visual attention.
775	Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks	Chong Li, C. J. Richard Shi	We present COBLA—Constrained Optimization Based Low-rank Approximation—a systematic method of finding an optimal low-rank approximation of a trained convolutional neural network, subject to constraints in the number of multiply-accumulate (MAC) operations and the memory footprint.
776	Stereo relative pose from line and point feature triplets	Alexander Vakhitov, Victor Lempitsky, Yinqiang Zheng	In this work we present two minimal solvers for stereo relative pose.