Paper Digest: ICCV 2013 Highlights

December 2, 2013October 6, 2019 admin

The International Conference on Computer Vision (ICCV) is one of the top computer vision conferences in the world. In 2013, it is to be held in Sydney, Australia.

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: ICCV 2013 Papers

	Title	Authors	Highlight
1	Latent Task Adaptation with Large-Scale Hierarchies	Yangqing Jia, Trevor Darrell	In this paper we propose a novel probabilistic model that jointly identifies the underlying task and performs prediction with a lineartime probabilistic inference algorithm, given a set of query images from a latent task.
2	Image Co-segmentation via Consistent Functional Maps	Fan Wang, Qixing Huang, Leonidas J. Guibas	In this paper, we aim to jointly segment a set of images starting from a small number of labeled images or none at all.
3	Manipulation Pattern Discovery: A Nonparametric Bayesian Approach	Bingbing Ni, Pierre Moulin	We aim to unsupervisedly discover human’s action (motion) patterns of manipulating various objects in scenarios such as assisted living.
4	Large-Scale Image Annotation by Efficient and Robust Kernel Metric Learning	Zheyun Feng, Rong Jin, Anil Jain	In this paper, we propose a robust kernel metric learning (RKML) algorithm based on the regression technique that is able to directly utilize image annotations.
5	Hybrid Deep Learning for Face Verification	Yi Sun, Xiaogang Wang, Xiaoou Tang	A key contribution of this work is to directly learn relational visual features, which indicate identity similarities, from raw pixels of face pairs with a hybrid deep network.
6	Latent Data Association: Bayesian Model Selection for Multi-target Tracking	Aleksandr V. Segal, Ian Reid	We propose a novel parametrization of the data association problem for multi-target tracking.
7	Recursive Estimation of the Stein Center of SPD Matrices and Its Applications	Hesamoddin Salehian, Guang Cheng, Baba C. Vemuri, Jeffrey Ho	In this paper we present a novel recursive estimator for center based on the Stein distance which is the square root of the LogDet divergence that is significantly faster than the batch mode computation of this center.
8	Real-Time Solution to the Absolute Pose Problem with Unknown Radial Distortion and Focal Length	Zuzana Kukelova, Martin Bujnak, Tomas Pajdla	In this paper we present a new solution to the absolute pose problem for camera with unknown radial distortion and unknown focal length from five 2D-to-3D point correspondences.
9	Sieving Regression Forest Votes for Facial Feature Detection in the Wild	Heng Yang, Ioannis Patras	In this paper we propose a method for the localization of multiple facial features on challenging face images.
10	Constant Time Weighted Median Filtering for Stereo Matching and Beyond	Ziyang Ma, Kaiming He, Yichen Wei, Jian Sun, Enhua Wu	In this work, we study weighted median filtering for disparity refinement.
11	Feature Weighting via Optimal Thresholding for Video Analysis	Zhongwen Xu, Yi Yang, Ivor Tsang, Nicu Sebe, Alexander G. Hauptmann	In this paper, we propose a novel feature fusion approach, namely Feature Weighting via Optimal Thresholding (FWOT) to effectively fuse various features.
12	Restoring an Image Taken through a Window Covered with Dirt or Rain	David Eigen, Dilip Krishnan, Rob Fergus	Instead, we present a post-capture image processing solution that can remove localized rain and dirt artifacts from a single image. We collect a dataset of clean/corrupted image pairs which are then used to train a specialized form of convolutional neural network.
13	Tracking via Robust Multi-task Multi-view Joint Sparse Representation	Zhibin Hong, Xue Mei, Danil Prokhorov, Dacheng Tao	In this paper, we cast tracking as a novel multi-task multi-view sparse learning problem and exploit the cues from multiple views including various types of visual features, such as intensity, color, and edge, where each feature observation can be sparsely represented by a linear combination of atoms from an adaptive feature dictionary.
14	A Simple Model for Intrinsic Image Decomposition with Depth Cues	Qifeng Chen, Vladlen Koltun	We present a model for intrinsic decomposition of RGB-D images.
15	Holistic Scene Understanding for 3D Object Detection with RGBD Cameras	Dahua Lin, Sanja Fidler, Raquel Urtasun	In this paper, we tackle the problem of indoor scene understanding using RGBD data.
16	Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model	Xiang Yu, Junzhou Huang, Shaoting Zhang, Wang Yan, Dimitris N. Metaxas	For face detection, we propose a group sparse learning method to automatically select the most salient facial landmarks.
17	Online Robust Non-negative Dictionary Learning for Visual Tracking	Naiyan Wang, Jingdong Wang, Dit-Yan Yeung	This paper studies the visual tracking problem in video sequences and presents a novel robust sparse tracker under the particle filter framework.
18	A Max-Margin Perspective on Sparse Representation-Based Classification	Zhaowen Wang, Jianchao Yang, Nasser Nasrabadi, Thomas Huang	In this paper, we present a novel perspective towards SRC and interpret it as a margin classifier.
19	Semantic Transform: Weakly Supervised Semantic Inference for Relating Visual Attributes	Sukrit Shankar, Joan Lasenby, Roberto Cipolla	In this paper, we introduce the Semantic Transform, which under minimal supervision, adaptively finds a semantic feature space along with a class ordering that is related in the best possible way.
20	Correlation Adaptive Subspace Segmentation by Trace Lasso	Canyi Lu, Jiashi Feng, Zhouchen Lin, Shuicheng Yan	In this work, we argue that both sparsity and the grouping effect are important for subspace segmentation.
21	DCSH – Matching Patches in RGBD Images	Yaron Eshet, Simon Korman, Eyal Ofek, Shai Avidan	We extend patch based methods to work on patches in 3D space.
22	Simultaneous Clustering and Tracklet Linking for Multi-face Tracking in Videos	Baoyuan Wu, Siwei Lyu, Bao-Gang Hu, Qiang Ji	We describe a novel method that simultaneously clusters and associates short sequences of detected faces (termed as face tracklets) in videos.
23	Subpixel Scanning Invariant to Indirect Lighting Using Quadratic Code Length	Nicolas Martin, Vincent Couture, Sebastien Roy	We present a scanning method that recovers dense subpixel camera-projector correspondence without requiring any photometric calibration nor preliminary knowledge of their relative geometry.
24	PM-Huber: PatchMatch with Huber Regularization for Stereo Matching	Philipp Heise, Sebastian Klose, Brian Jensen, Alois Knoll	This work presents a method that integrates the PatchMatch stereo algorithm into a variational smoothing formulation using quadratic relaxation.
25	Relative Attributes for Large-Scale Abandoned Object Detection	Quanfu Fan, Prasad Gabbur, Sharath Pankanti	With these features, we apply a linear ranking algorithm to sort alerts according to their relevance to the end-user.
26	Random Grids: Fast Approximate Nearest Neighbors and Range Searching for Image Search	Dror Aiger, Efi Kokiopoulou, Ehud Rivlin	We propose two solutions for both nearest neighbors and range search problems.
27	Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation	David Ferstl, Christian Reinbacher, Rene Ranftl, Matthias Ruether, Horst Bischof	In this work we present a novel method for the challenging problem of depth image upsampling. Furthermore, we introduce novel datasets with highly accurate groundtruth, which, for the first time, enable to benchmark depth upsampling methods using real sensor data.
28	3D Scene Understanding by Voxel-CRF	Byung-Soo Kim, Pushmeet Kohli, Silvio Savarese	In this paper we propose a new method that allows us to jointly refine the 3D reconstruction of the scene (raw depth values) while accurately segmenting out the objects or scene elements from the 3D reconstruction.
29	No Matter Where You Are: Flexible Graph-Guided Multi-task Learning for Multi-view Head Pose Classification under Target Motion	Yan Yan, Elisa Ricci, Ramanathan Subramanian, Oswald Lanz, Nicu Sebe	We propose a novel Multi-Task Learning framework (FEGA-MTL) for classifying the head pose of a person who moves freely in an environment monitored by multiple, large field-of-view surveillance cameras.
30	Dynamic Probabilistic Volumetric Models	Ali Osman Ulusoy, Octavian Biris, Joseph L. Mundy	This paper presents a probabilistic volumetric framework for image based modeling of general dynamic 3-d scenes.
31	Predicting an Object Location Using a Global Image Representation	Jose A. Rodriguez Serrano, Diane Larlus	This article proposes two contributions: (i) a metric learning algorithm and (ii) a representation of images as object probability maps, that are both optimized for detection.
32	Anchored Neighborhood Regression for Fast Example-Based Super-Resolution	Radu Timofte, Vincent De Smet, Luc Van Gool	This paper proposes fast super-resolution methods while making no compromise on quality.
33	Robust Object Tracking with Online Multi-lifespan Dictionary Learning	Junliang Xing, Jin Gao, Bing Li, Weiming Hu, Shuicheng Yan	In this work, we address the object template building and updating problem in these 1 -tracking approaches, which has not been fully studied.
34	Finding the Best from the Second Bests – Inhibiting Subjective Bias in Evaluation of Visual Tracking Algorithms	Yu Pang, Haibin Ling	Using these records, we derive performance rankings of the involved trackers by four different methods.
35	Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions	Mohamed Elhoseiny, Babak Saleh, Ahmed Elgammal	We propose an approach for zero-shot learning of object categories where the description of unseen categories comes in the form of typical text such as an encyclopedia entry, without the need to explicitly defined attributes.
36	Detecting Dynamic Objects with Multi-view Background Subtraction	Raul Diaz, Sam Hallman, Charless C. Fowlkes	In this paper, we investigate how such information can be used to improve the detection of dynamic objects such as pedestrians and cars.
37	Face Recognition via Archetype Hull Ranking	Yuanjun Xiong, Wei Liu, Deli Zhao, Xiaoou Tang	In this paper, we migrate such a geometric model to address face recognition and verification together through proposing a unified archetype hull ranking framework.
38	Compositional Models for Video Event Detection: A Multiple Kernel Learning Latent Variable Approach	Arash Vahdat, Kevin Cannons, Greg Mori, Sangmin Oh, Ilseo Kim	We present a compositional model for video event detection.
39	Nested Shape Descriptors	Jeffrey Byrne, Jianbo Shi	In this paper, we propose a new family of binary local feature descriptors called nested shape descriptors.
40	Coarse-to-Fine Semantic Video Segmentation Using Supervoxel Trees	Aastha Jain, Shuanak Chatterjee, Rene Vidal	We propose an exact, general and efficient coarse-to-fine energy minimization strategy for semantic video segmentation.
41	Local Signal Equalization for Correspondence Matching	Derek Bradley, Thabo Beeler	In this paper we propose a local signal equalization approach for correspondence matching.
42	On One-Shot Similarity Kernels: Explicit Feature Maps and Properties	Stefanos Zafeiriou, Irene Kotsia	In this paper, we attempt the derivation of explicit feature maps of a recently proposed class of kernels, the so-called one-shot similarity kernels.
43	Combining the Right Features for Complex Event Recognition	Kevin Tang, Bangpeng Yao, Li Fei-Fei, Daphne Koller	In this paper, we tackle the problem of combining features extracted from video for complex event recognition.
44	NEIL: Extracting Visual Knowledge from Web Data	Xinlei Chen, Abhinav Shrivastava, Abhinav Gupta	We propose NEIL (Never Ending Image Learner), a computer program that runs 24 hours per day and 7 days per week to automatically extract visual knowledge from Internet data.
45	Joint Subspace Stabilization for Stereoscopic Video	Feng Liu, Yuzhen Niu, Hailin Jin	In this paper, we present a joint subspace stabilization method for stereoscopic video.
46	Learning CRFs for Image Parsing with Adaptive Subgradient Descent	Honghui Zhang, Jingdong Wang, Ping Tan, Jinglu Wang, Long Quan	We propose an adaptive subgradient descent method to efficiently learn the parameters of CRF models for image parsing.
47	Box in the Box: Joint 3D Layout and Object Reasoning from Single Images	Alexander G. Schwing, Sanja Fidler, Marc Pollefeys, Raquel Urtasun	In this paper we propose an approach to jointly infer the room layout as well as the objects present in the scene.
48	A Global Linear Method for Camera Pose Registration	Nianjuan Jiang, Zhaopeng Cui, Ping Tan	We present a linear method for global camera pose registration from pairwise relative poses encoded in essential matrices.
49	Heterogeneous Image Features Integration via Multi-modal Semi-supervised Learning Model	Xiao Cai, Feiping Nie, Weidong Cai, Heng Huang	In this paper, we propose a novel approach to integrate heterogeneous features by performing multi-modal semi-supervised classification on unlabeled as well as unsegmented images.
50	3DNN: Viewpoint Invariant 3D Geometry Matching for Scene Understanding	Scott Satkin, Martial Hebert	We present a new algorithm 3DNN (3D NearestNeighbor), which is capable of matching an image with 3D data, independently of the viewpoint from which the image was captured.
51	Correntropy Induced L2 Graph for Robust Subspace Clustering	Canyi Lu, Jinhui Tang, Min Lin, Liang Lin, Shuicheng Yan, Zhouchen Lin	In this paper, we study the robust subspace clustering problem, which aims to cluster the given possibly noisy data points into their underlying subspaces.
52	Unsupervised Domain Adaptation by Domain Invariant Projection	Mahsa Baktashmotlagh, Mehrtash T. Harandi, Brian C. Lovell, Mathieu Salzmann	In this paper, we introduce a Domain Invariant Projection approach: An unsupervised domain adaptation method that overcomes this issue by extracting the information that is invariant across the source and target domains.
53	Large-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences	Frank Steinbrucker, Christian Kerl, Daniel Cremers	We propose a method to generate highly detailed, textured 3D models of large environments from RGB-D sequences.
54	Detecting Curved Symmetric Parts Using a Deformable Disc Model	Tom Sie Ho Lee, Sanja Fidler, Sven Dickinson	Drawing on the concept of a medial axis, defined as the locus of centers of maximal inscribed discs that sweep out a symmetric part, we model part recovery as the search for a sequence of deformable maximal inscribed disc hypotheses generated from a multiscale superpixel segmentation, a framework proposed by [13].
55	Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation	Yuandong Tian, Srinivasa G. Narasimhan	In this work, we develop a hierarchical structure for the Nearest Neighbor estimators, each of which can have only a local image support.
56	Recognising Human-Object Interaction via Exemplar Based Modelling	Jian-Fang Hu, Wei-Shi Zheng, Jianhuang Lai, Shaogang Gong, Tao Xiang	To overcome this limitation, a novel exemplar based approach is proposed in this work.
57	How Do You Tell a Blackbird from a Crow?	Thomas Berg, Peter N. Belhumeur	In the context of fine-grained visual categorization, we show that we can automatically determine which classes are most visually similar, discover what visual features distinguish very similar classes, and illustrate the key features in a way meaningful to humans.
58	Video Synopsis by Heterogeneous Multi-source Correlation	Xiatian Zhu, Chen Change Loy, Shaogang Gong	In contrast to existing video synopsis approaches that rely on visual cues alone, we propose a novel multi-source synopsis framework capable of correlating visual data and independent non-visual auxiliary information to better describe and summarise subtle physical events in complex scenes.
59	Semantic Segmentation without Annotating Segments	Wei Xia, Csaba Domokos, Jian Dong, Loong-Fah Cheong, Shuicheng Yan	In this paper, we address semantic segmentation assuming that object bounding boxes are provided by object detectors, but no training data with annotated segments are available.
60	Action Recognition with Actons	Jun Zhu, Baoyuan Wang, Xiaokang Yang, Wenjun Zhang, Zhuowen Tu	In this paper, we propose a two-layer structure for action recognition to automatically exploit a mid-level “acton” representation.
61	Exemplar Cut	Jimei Yang, Yi-Hsuan Tsai, Ming-Hsuan Yang	We present a hybrid parametric and nonparametric algorithm, exemplar cut, for generating class-specific object segmentation hypotheses.
62	Discovering Object Functionality	Bangpeng Yao, Jiayuan Ma, Li Fei-Fei	In this paper, we propose a weakly supervised approach to discover all possible object functionalities.
63	Saliency Detection: A Boolean Map Approach	Jianming Zhang, Stan Sclaroff	A novel Boolean Map based Saliency (BMS) model is proposed.
64	Active MAP Inference in CRFs for Efficient Semantic Segmentation	Gemma Roig, Xavier Boix, Roderick De Nijs, Sebastian Ramos, Koljia Kuhnlenz, Luc Van Gool	In this paper, we focus on CRFs where the computational cost of instantiating the potentials is orders of magnitude higher than MAP inference.
65	PixelTrack: A Fast Adaptive Algorithm for Tracking Non-rigid Objects	Stefan Duffner, Christophe Garcia	In this paper, we present a novel algorithm for fast tracking of generic objects in videos.
66	Class-Specific Simplex-Latent Dirichlet Allocation for Image Classification	Mandar Dixit, Nikhil Rasiwasia, Nuno Vasconcelos	To address this, we introduce a model that induces supervision in topic discovery, while retaining the original flexibility of LDA to account for unanticipated structures of interest.
67	BOLD Features to Detect Texture-less Objects	Federico Tombari, Alessandro Franchi, Luigi Di Stefano	We propose to tackle this problem by a compact and distinctive representation of groups of neighboring line segments aggregated over limited spatial supports and invariant to rotation, translation and scale changes.
68	Bird Part Localization Using Exemplar-Based Models with Enforced Pose and Subcategory Consistency	Jiongxin Liu, Peter N. Belhumeur	In this paper, we propose a novel approach for bird part localization, targeting fine-grained categories with wide variations in appearance due to different poses (including aspect and orientation) and subcategories.
69	Multiple Non-rigid Surface Detection and Registration	Yi Wu, Yoshihisa Ijiri, Ming-Hsuan Yang	In this work, we propose an algorithm that detects and registers multiple nonrigid instances of given objects in a cluttered image.
70	Drosophila Embryo Stage Annotation Using Label Propagation	Tomas Kazmar, Evgeny Z. Kvon, Alexander Stark, Christoph H. Lampert	In this work we propose a system for automatic classification of Drosophila embryos into developmental stages.
71	Parsing IKEA Objects: Fine Pose Estimation	Joseph J. Lim, Hamed Pirsiavash, Antonio Torralba	We address the problem of localizing and estimating the fine-pose of objects in the image with exact 3D models. Moreover, we also provide a new dataset containing fine-aligned objects with their exactly matched 3D models, and a set of models for widely used objects.
72	Corrected-Moment Illuminant Estimation	Graham D. Finlayson	The best algorithms – now often built on top of existing feature extraction and machine learning – are only about twice as good as the simplest approaches.
73	Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps	Jiajia Luo, Wei Wang, Hairong Qi	In this paper, a new framework based on sparse coding and temporal pyramid matching (TPM) is proposed for depthbased human action recognition.
74	Online Video SEEDS for Temporal Window Objectness	Michael Van Den Bergh, Gemma Roig, Xavier Boix, Santiago Manen, Luc Van Gool	We introduce an online, real-time video superpixel algorithm based on the recently proposed SEEDS superpixels.
75	Fast Subspace Search via Grassmannian Based Hashing	Xu Wang, Stefan Atev, John Wright, Gilad Lerman	We present a new approach to approximate nearest subspace search, based on a simple, new locality sensitive hash for subspaces.
76	Data-Driven 3D Primitives for Single Image Understanding	David F. Fouhey, Abhinav Gupta, Martial Hebert	We argue that these primitives should be both visually discriminative and geometrically informative and we present a technique for discovering such primitives.
77	Partial Enumeration and Curvature Regularization	Carl Olsson, Johannes Ulen, Yuri Boykov, Vladimir Kolmogorov	We propose a general minimization approach for large graphs based on enumeration of labelings of certain small patches.
78	Fast Face Detector Training Using Tailored Views	Kristina Scherbaum, James Petterson, Rogerio S. Feris, Volker Blanz, Hans-Peter Seidel	This paper takes a look into the automated generation of adaptive training samples from a 3D morphable face model.
79	Image Retrieval Using Textual Cues	Anand Mishra, Karteek Alahari, C.V. Jawahar	We present an approach for the text-to-image retrieval problem based on textual content present in images.
80	Fluttering Pattern Generation Using Modified Legendre Sequence for Coded Exposure Imaging	Hae-Gon Jeon, Joon-Young Lee, Yudeog Han, Seon Joo Kim, In So Kweon	In this paper, we present a new computationally efficient algorithm for generating the binary sequence, which is especially well suited for longer sequences.
81	Prime Object Proposals with Randomized Prim’s Algorithm	Santiago Manen, Matthieu Guillaumin, Luc Van Gool	In this paper, we introduce a novel and very efficient method for generic object detection based on a randomized version of Prim’s algorithm.
82	Optimization Problems for Fast AAM Fitting in-the-Wild	Georgios Tzimiropoulos, Maja Pantic	We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions.
83	Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization	Hua Wang, Feiping Nie, Weidong Cai, Heng Huang	In this paper, we address these weaknesses by learning a Semi-Supervised Robust Dictionary (SSR-D).
84	Cosegmentation and Cosketch by Unsupervised Learning	Jifeng Dai, Ying Nian Wu, Jie Zhou, Song-Chun Zhu	To address this issue, we propose an unsupervised learning framework for cosegmentation, by coupling cosegmentation with what we call “cosketch”.
85	Joint Learning of Discriminative Prototypes and Large Margin Nearest Neighbor Classifiers	Martin Kostinger, Paul Wohlhart, Peter M. Roth, Horst Bischof	In this paper, we raise important issues concerning the evaluation complexity of existing Mahalanobis metric learning methods.
86	Joint Optimization for Consistent Multiple Graph Matching	Junchi Yan, Yu Tian, Hongyuan Zha, Xiaokang Yang, Ya Zhang, Stephen M. Chu	Joint Optimization for Consistent Multiple Graph Matching
87	Scene Collaging: Analysis and Synthesis of Natural Images with Semantic Layers	Phillip Isola, Ce Liu	In this paper, we propose to use a similar process in order to parse a scene.
88	Quadruplet-Wise Image Similarity Learning	Marc T. Law, Nicolas Thome, Matthieu Cord	This paper introduces a novel similarity learning framework.
89	Facial Action Unit Event Detection by Cascade of Tasks	Xiaoyu Ding, Wen-Sheng Chu, Fernando De La Torre, Jeffery F. Cohn, Qiao Wang	In this paper, we propose a method called Cascade of Tasks (CoT) that combines the use of different tasks (i.e., frame, segment and transition) for AU event detection.
90	Cascaded Shape Space Pruning for Robust Facial Landmark Detection	Xiaowei Zhao, Shiguang Shan, Xiujuan Chai, Xilin Chen	In this paper, we propose a novel cascaded face shape space pruning algorithm for robust facial landmark detection.
91	Efficient Higher-Order Clustering on the Grassmann Manifold	Suraj Jain, Venu Madhav Govindu	In this paper we present our approach of Sparse Grassmann Clustering (SGC) that combines attributes of both categories.
92	A Scalable Unsupervised Feature Merging Approach to Efficient Dimensionality Reduction of High-Dimensional Visual Data	Lingqiao Liu, Lei Wang	To address this problem, we formulate unsupervised feature merging as a PCA problem imposed with a special structure constraint.
93	Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction	Ning Zhang, Ryan Farrell, Forrest Iandola, Trevor Darrell	This paper proposes two pose-normalized descriptors based on computationally-efficient deformable part models.
94	Compensating for Motion during Direct-Global Separation	Supreeth Achar, Stephen T. Nuske, Srinivasa G. Narasimhan	In this paper, we develop a motion compensation method that relaxes this condition and allows direct-global separation to be performed on video sequences of dynamic scenes captured by moving projector-camera systems.
95	Shufflets: Shared Mid-level Parts for Fast Object Detection	Iasonas Kokkinos	We present a method to identify and exploit structures that are shared across different object categories, by using sparse coding to learn a shared basis for the ‘part’ and ‘root’ templates of Deformable Part Models (DPMs).
96	GrabCut in One Cut	Meng Tang, Lena Gorelick, Olga Veksler, Yuri Boykov	We propose a new energy term explicitly measuring L 1 distance between the object and background appearance models that can be globally maximized in one graph cut.
97	Coupling Alignments with Recognition for Still-to-Video Face Recognition	Zhiwu Huang, Xiaowei Zhao, Shiguang Shan, Ruiping Wang, Xilin Chen	In this paper, we discover that the interactions among the three tasks-quality alignment, geometric alignment and face recognition-can benefit from each other, thus should be performed jointly.
98	Stacked Predictive Sparse Coding for Classification of Distinct Regions in Tumor Histopathology	Hang Chang, Yin Zhou, Paul Spellman, Bahram Parvin	We propose a system that automatically learns a series of basis functions for representing the underlying spatial distribution using stacked predictive sparse decomposition (PSD).
99	Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval	Cai-Zhi Zhu, Herve Jegou, Shin Ichi Satoh	Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval
100	Direct Optimization of Frame-to-Frame Rotation	Laurent Kneip, Simon Lynen	Two global optimization approaches are proposed.
101	Unsupervised Intrinsic Calibration from a Single Frame Using a “Plumb-Line” Approach	R. Melo, M. Antunes, J.P. Barreto, G. Falcao, N. Goncalves	We propose a new framework for the unsupervised simultaneous detection of natural image of lines and camera parameters estimation, enabling a robust calibration from a single image.
102	Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria	Christoph Straehle, Ullrich Koethe, Fred A. Hamprecht	We propose a scheme that allows to partition an image into a previously unknown number of segments, using only minimal supervision in terms of a few must-link and cannotlink annotations.
103	Discriminant Tracking Using Tensor Representation with Semi-supervised Improvement	Jin Gao, Junliang Xing, Weiming Hu, Steve Maybank	In this paper, we address an image as a 2 nd -order tensor in its original form, and find a discriminative linear embedding space approximation to the original nonlinear submanifold embedded in the tensor space based on the graph embedding framework.
104	Adapting Classification Cascades to New Domains	Vidit Jain, Sachin Sudhakar Farfade	Here we present an algorithm for quickly adapting a pre-trained cascade of classifiers using a small number of labeled positive instances from a different yet similar data domain.
105	Collaborative Active Learning of a Kernel Machine Ensemble for Recognition	Gang Hua, Chengjiang Long, Ming Yang, Yan Gao	We present a collaborative computational model for active learning with multiple human oracles.
106	Accurate and Robust 3D Facial Capture Using a Single RGBD Camera	Yen-Lin Chen, Hsiang-Tao Wu, Fuhao Shi, Xin Tong, Jinxiang Chai	This paper presents an automatic and robust approach that accurately captures high-quality 3D facial performances using a single RGBD camera.
107	Domain Adaptive Classification	Fatemeh Mirrashed, Mohammad Rastegari	We propose an unsupervised domain adaptation method that exploits intrinsic compact structures of categories across different domains using binary attributes.
108	GOSUS: Grassmannian Online Subspace Updates with Structured-Sparsity	Jia Xu, Vamsi K. Ithapu, Lopamudra Mukherjee, James M. Rehg, Vikas Singh	We propose an efficient numerical solution, GOSUS, Grassmannian Online ficintnnumeriallsowith n,GGOSSUUS,GGrasssmaafor this problem.
109	Analysis of Scores, Datasets, and Models in Visual Saliency Prediction	Ali Borji, Hamed R. Tavakoli, Dicky N. Sihite, Laurent Itti	In this study, we pursue a critical and quantitative look at challenges (e.g., center-bias, map smoothing) in saliency modeling and the way they affect model accuracy.
110	A Color Constancy Model with Double-Opponency Mechanisms	Shaobing Gao, Kaifu Yang, Chaoyi Li, Yongjie Li	We introduce a new color constancy model by imitating the functional properties of the HVS from the retina to the double-opponent cells in V1.
111	Latent Multitask Learning for View-Invariant Action Recognition	Behrooz Mahasseni, Sinisa Todorovic	This paper presents an approach to view-invariant action recognition, where human poses and motions exhibit large variations across different camera viewpoints.
112	Translating Video Content to Natural Language Descriptions	Marcus Rohrbach, Wei Qiu, Ivan Titov, Stefan Thater, Manfred Pinkal, Bernt Schiele	In order to provide natural language descriptions for visual content, this paper combines two important ingredients.
113	Robust Dictionary Learning by Error Source Decomposition	Zhuoyuan Chen, Ying Wu	We propose a general method to decompose the reconstructive residual into two components: a non-sparse component for small universal noises and a sparse component for large outliers, respectively.
114	Accurate Blur Models vs. Image Priors in Single Image Super-resolution	Netalee Efrat, Daniel Glasner, Alexander Apartsin, Boaz Nadler, Anat Levin	In this work, we examine the relative importance of the image prior and the reconstruction constraint.
115	Monte Carlo Tree Search for Scheduling Activity Recognition	Mohamed R. Amer, Sinisa Todorovic, Alan Fern, Song-Chun Zhu	This paper presents an efficient approach to video parsing.
116	Multi-stage Contextual Deep Learning for Pedestrian Detection	Xingyu Zeng, Wanli Ouyang, Xiaogang Wang	In this paper, we propose a new deep model that can jointly train multi-stage classifiers through several stages of backpropagation.
117	Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias	Chen Fang, Ye Xu, Daniel N. Rockmore	In this work we propose Unbiased Metric Learning (UML), a metric learning approach, to achieve this goal.
118	Pyramid Coding for Functional Scene Element Recognition in Video Scenes	Eran Swears, Anthony Hoogs, Kim Boyer	Pyramid Coding for Functional Scene Element Recognition in Video Scenes
119	Fast Object Segmentation in Unconstrained Video	Anestis Papazoglou, Vittorio Ferrari	We present a technique for separating foreground objects from the background in a video.
120	Offline Mobile Instance Retrieval with a Small Memory Footprint	Jayaguru Panda, Michael S. Brown, C.V. Jawahar	To achieve this, we describe a set of strategies that can reduce the visual index up to 60-80 x compared to a standard instance retrieval implementation found on desktops or servers.
121	Contextual Hypergraph Modeling for Salient Object Detection	Xi Li, Yao Li, Chunhua Shen, Anthony Dick, Anton Van Den Hengel	In this work, we model an image as a hypergraph that utilizes a set of hyperedges to capture the contextual properties of image pixels or regions.
122	Automatic Kronecker Product Model Based Detection of Repeated Patterns in 2D Urban Images	Juan Liu, Emmanouil Psarakis, Ioannis Stamos	After rectifying the input images, we describe novel algorithms that extract repeated patterns by using Kronecker product based modeling that is based on a solid theoretical foundation.
123	From Where and How to What We See	S. Karthikeyan, Vignesh Jagadeesh, Renuka Shenoy, Miguel Ecksteinz, B.S. Manjunath	In this paper we explore a novel problem of predicting face and text regions in images using eye tracking data from multiple subjects. We also present a new eye tracking dataset on 300 images selected from ICDAR, Street-view, Flickr and Oxford-IIIT Pet Dataset from 15 subjects.
124	Saliency Detection via Absorbing Markov Chain	Bowen Jiang, Lihe Zhang, Huchuan Lu, Chuan Yang, Ming-Hsuan Yang	In this paper, we formulate saliency detection via absorbing Markov chain on an image graph model.
125	Semantic-Aware Co-indexing for Image Retrieval	Shiliang Zhang, Ming Yang, Xiaoyu Wang, Yuanqing Lin, Qi Tian	In this paper, for vocabulary tree based image retrieval, we propose a semantic-aware co-indexing algorithm to jointly embed two strong cues into the inverted indexes: 1) local invariant features that are robust to delineate low-level image contents, and 2) semantic attributes from large-scale object recognition that may reveal image semantic meanings.
126	Stable Hyper-pooling and Query Expansion for Event Detection	Matthijs Douze, Jerome Revaud, Cordelia Schmid, Herve Jegou	This paper makes two complementary contributions to event retrieval in large collections of videos.
127	Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation	Suyog Dutt Jain, Kristen Grauman	Whereas existing methods assume a fixed form of input no matter the image, we propose to predict the tradeoff between accuracy and effort.
128	What is the Most Efficient Way to Select Nearest Neighbor Candidates for Fast Approximate Nearest Neighbor Search?	Masakazu Iwamura, Tomokazu Sato, Koichi Kise	In this paper, we propose a new ANNS method that takes into account costs in the selection process.
129	Fast High Dimensional Vector Multiplication Face Recognition	Oren Barkan, Jonathan Weill, Lior Wolf, Hagai Aronowitz	This paper advances descriptor-based face recognition by suggesting a novel usage of descriptors to form an over-complete representation, and by proposing a new metric learning pipeline within the same/not-same framework.
130	Group Norm for Learning Structured SVMs with Unstructured Latent Variables	Daozheng Chen, Dhruv Batra, William T. Freeman	The goal of this paper is to regularize the complexity of the latent space and learn which hidden states are really relevant for prediction.
131	New Graph Structured Sparsity Model for Multi-label Image Annotations	Xiao Cai, Feiping Nie, Weidong Cai, Heng Huang	In this paper, we model the label correlations using the relational graph, and propose a novel graph structured sparse learning model to incorporate the topological constraints of relation graph in multi-label classifications.
132	Real-Time Body Tracking with One Depth Camera and Inertial Sensors	Thomas Helten, Meinard Muller, Hans-Peter Seidel, Christian Theobalt	In this paper, we present a novel sensor fusion approach for real-time full body tracking that succeeds in such difficult situations.
133	Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks	Mojtaba Seyedhosseini, Mehdi Sajjadi, Tolga Tasdizen	To address this challenge, we propose a multi-resolution contextual framework, called cascaded hierarchical model (CHM), which learns contextual information in a hierarchical framework for image segmentation.
134	Low-Rank Sparse Coding for Image Classification	Tianzhu Zhang, Bernard Ghanem, Si Liu, Changsheng Xu, Narendra Ahuja	In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification.
135	Learning to Rank Using Privileged Information	Viktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert	In this work, we study the case where we are given additional information about the training data, which however will not be available at test time.
136	Extrinsic Camera Calibration without a Direct View Using Spherical Mirror	Amit Agrawal	In this paper, we show that the pose can be obtained using a single reflection in a spherical mirror of known radius.
137	Two-Point Gait: Decoupling Gait from Body Shape	Stephen Lombardi, Ko Nishino, Yasushi Makihara, Yasushi Yagi	In this paper, we introduce Two-Point Gait, a gait representation that encodes the limb motions regardless of the body shape.
138	Robust Subspace Clustering via Half-Quadratic Minimization	Yingya Zhang, Zhenan Sun, Ran He, Tieniu Tan	A novel optimization model for robust subspace clustering is proposed in this paper.
139	Category-Independent Object-Level Saliency Detection	Yangqing Jia, Mei Han	In this paper, we propose an efficient way to combine such high-level saliency priors and low-level appearance models.
140	A Method of Perceptual-Based Shape Decomposition	Chang Ma, Zhongqian Dong, Tingting Jiang, Yizhou Wang, Wen Gao	In this paper, we propose a novel perception-based shape decomposition method which aims to decompose a shape into semantically meaningful parts.
141	Bayesian Robust Matrix Factorization for Image and Video Processing	Naiyan Wang, Dit-Yan Yeung	To benefit from the strengths of full Bayesian treatment over point estimation, we propose here a full Bayesian approach to robust matrix factorization.
142	Measuring Flow Complexity in Videos	Saad Ali	In this paper a notion of flow complexity that measures the amount of interaction among objects is introduced and an approach to compute it directly from a video sequence is proposed.
143	DeepFlow: Large Displacement Optical Flow with Deep Matching	Philippe Weinzaepfel, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid	We propose a descriptor matching algorithm, tailored to the optical flow problem, that allows to boost performance on fast motions.
144	The Way They Move: Tracking Multiple Targets with Similar Appearance	Caglayan Dicle, Octavia I. Camps, Mario Sznaier	We introduce a computationally efficient algorithm for multi-object tracking by detection that addresses four main challenges: appearance similarity among targets, missing data due to targets being out of the field of view or occluded behind other objects, crossing trajectories, and camera motion.
145	What Do You Do? Occupation Recognition in a Photo via Social Context	Ming Shao, Liangyue Li, Yun Fu	In this paper, we investigate the problem of recognizing occupations of multiple people with arbitrary poses in a photo.
146	Pose Estimation and Segmentation of People in 3D Movies	Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev	We seek to obtain a pixel-wise segmentation and pose estimation of multiple people in a stereoscopic video. Second, we introduce a stereoscopic dataset with frames extracted from feature-length movies “StreetDance 3D” and “Pina”.
147	Calibration-Free Gaze Estimation Using Human Gaze Patterns	Fares Alnajar, Theo Gevers, Roberto Valenti, Sennay Ghebreab	We present a novel method to auto-calibrate gaze estimators based on gaze patterns obtained from other viewers.
148	Lifting 3D Manhattan Lines from a Single Image	Srikumar Ramalingam, Matthew Brand	We propose a novel and an efficient method for reconstructing the 3D arrangement of lines extracted from a single image, using vanishing points, orthogonal structure, and an optimization procedure that considers all plausible connectivity constraints between lines.
149	A Framework for Shape Analysis via Hilbert Space Embedding	Sadeep Jayasumana, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi	We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall’s shape manifold.
150	Structured Forests for Fast Edge Detection	Piotr Dollar, C. L. Zitnick	In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector.
151	Scene Text Localization and Recognition with Oriented Stroke Detection	Lukas Neumann, Jiri Matas	An unconstrained end-to-end text localization and recognition method is presented.
152	CoDeL: A Human Co-detection and Labeling Framework	Jianping Shi, Renjie Liao, Jiaya Jia	We propose a co-detection and labeling (CoDeL) framework to identify persons that contain self-consistent appearance in multiple images.
153	Exploiting Reflection Change for Automatic Reflection Removal	Yu Li, Michael S. Brown	This paper introduces an automatic method for removing reflection interference when imaging a scene behind a glass surface.
154	Elastic Net Constraints for Shape Matching	Emanuele Rodola, Andrea Torsello, Tatsuya Harada, Yasuo Kuniyoshi, Daniel Cremers	In order to control the accuracy/sparsity trade-off we introduce a weighting parameter on the combination of two existing relaxations, namely spectral and
155	A New Adaptive Segmental Matching Measure for Human Activity Recognition	Shahriar Shariat, Vladimir Pavlovic	In this paper we propose a fast and effective segmental alignmentbased method that is able to classify activities and interactions in complex environments.
156	A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse Coding	Wangmeng Zuo, Deyu Meng, Lei Zhang, Xiangchu Feng, David Zhang	In this paper, by extending the popular soft-thresholding operator, we propose a generalized iterated shrinkage algorithm (GISA) for p -norm non-convex sparse coding.
157	Robust Tucker Tensor Decomposition for Effective Image Representation	Miao Zhang, Chris Ding	In this paper, we propose a robust Tucker tensor decomposition model (RTD) to suppress the influence of outliers, which uses L 1 -norm loss function.
158	Learning Graphs to Match	Minsu Cho, Karteek Alahari, Jean Ponce	This paper presents an effective scheme to parameterize a graph model, and learn its structural attributes for visual object matching.
159	SGTD: Structure Gradient and Texture Decorrelating Regularization for Image Decomposition	Qiegen Liu, Jianbo Liu, Pei Dong, Dong Liang	This paper presents a novel structure gradient and texture decorrelating regularization (SGTD) for image decomposition.
160	Discovering Details and Scene Structure with Hierarchical Iconoid Shift	Tobias Weyand, Bastian Leibe	We propose Hierarchical Iconoid Shift, a novel landmark clustering algorithm capable of discovering such details.
161	Single-Patch Low-Rank Prior for Non-pointwise Impulse Noise Removal	Ruixuan Wang, Emanuele Trucco	Based on this prior, we propose a single-patch method within a generalized joint low-rank and sparse matrix recovery framework to simultaneously detect and remove non-pointwise random-valued impulse noise (e.g., very small blobs).
162	Separating Reflective and Fluorescent Components Using High Frequency Illumination in the Spectral Domain	Ying Fu, Antony Lam, Imari Sato, Takahiro Okabe, Yoichi Sato	In this paper, we demonstrate efficient separation and recovery of reflective and fluorescent emission spectra through the use of high frequency illumination in the spectral domain.
163	Learning to Predict Gaze in Egocentric Video	Yin Li, Alireza Fathi, James M. Rehg	We present a model for gaze prediction in egocentric video by leveraging the implicit cues that exist in camera wearer’s behaviors.
164	Fine-Grained Categorization by Alignments	E. Gavves, B. Fernando, C.G.M. Snoek, A.W.M. Smeulders, T. Tuytelaars	The aim of this paper is fine-grained categorization without human interaction.
165	Symbiotic Segmentation and Part Localization for Fine-Grained Categorization	Yuning Chai, Victor Lempitsky, Andrew Zisserman	We propose a new method for the task of fine-grained visual categorization.
166	Learning People Detectors for Tracking in Crowded Scenes	Siyu Tang, Mykhaylo Andriluka, Anton Milan, Konrad Schindler, Stefan Roth, Bernt Schiele	In this paper we argue that for best performance one should explicitly train people detectors on failure cases of the overall tracker instead.
167	SIFTpack: A Compact Representation for Efficient SIFT Matching	Alexandra Gilinsky, Lihi Zelnik Manor	In this paper we propose the SIFTpack: a compact way of storing SIFT descriptors, which enables significantly faster calculations between sets of SIFTs than the current solutions.
168	Forward Motion Deblurring	Shicheng Zheng, Li Xu, Jiaya Jia	We start with the study of geometric models and analyze the difficulty of existing methods to deal with them.
169	HOGgles: Visualizing Object Detection Features	Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba	We introduce algorithms to visualize feature spaces used by object detectors.
170	Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose?	Elisabeta Marinoiu, Dragos Papava, Cristian Sminchisescu	In this paper we aim to unveil some of the processing-as well as the levels of accuracy-involved in the 3D perception of people from images by assessing the human performance.
171	EVSAC: Accelerating Hypotheses Generation by Modeling Matching Scores with Extreme Value Theory	Victor Fragoso, Pradeep Sen, Sergio Rodriguez, Matthew Turk	In this paper, we present a probabilistic parametric model that allows us to assign confidence values for each matching correspondence and therefore accelerates the generation of hypothesis models for RANSAC under these conditions.
172	Conservation Tracking	Martin Schiegg, Philipp Hanslovsky, Bernhard X. Kausler, Lars Hufnagel, Fred A. Hamprecht	The tracking model we present implements global consistency constraints for the number of targets comprised by each detection and is solved to global optimality on reasonably large 2D+t and 3D+t datasets.
173	Multiview Photometric Stereo Using Planar Mesh Parameterization	Jaesik Park, Sudipta N. Sinha, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon	We propose a method for accurate 3D shape reconstruction using uncalibrated multiview photometric stereo.
174	Handling Uncertain Tags in Visual Recognition	Arash Vahdat, Greg Mori	We develop the FlipSVM, a novel algorithm for handling these noisy, structured labels.
175	Finding Causal Interactions in Video Sequences	Mustafa Ayazoglu, Burak Yilmaz, Mario Sznaier, Octavia Camps	As shown in the paper, this leads to a block-sparsification problem that can be efficiently solved using a modified Group-Lasso type approach, capable of handling missing data and outliers (due for instance to occlusion and mis-identified correspondences).
176	A Non-parametric Bayesian Network Prior of Human Pose	Andreas M. Lehrmann, Peter V. Gehler, Sebastian Nowozin	In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions.
177	Topology-Constrained Layered Tracking with Latent Flow	Jason Chang, John W. Fisher III	We present an integrated probabilistic model for layered object tracking that combines dynamics on implicit shape representations, topological shape constraints, adaptive appearance models, and layered flow.
178	Saliency Detection via Dense and Sparse Reconstruction	Xiaohui Li, Huchuan Lu, Lihe Zhang, Xiang Ruan, Ming-Hsuan Yang	In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction errors.
179	Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time	Yong Jae Lee, Alexei A. Efros, Martial Hebert	We present a weakly-supervised visual data mining approach that discovers connections between recurring midlevel visual elements in historic (temporal) and geographic (spatial) image collections, and attempts to capture the underlying visual style.
180	Synergistic Clustering of Image and Segment Descriptors for Unsupervised Scene Understanding	Daniel M. Steinberg, Oscar Pizarro, Stefan B. Williams	To this end, we present a totally unsupervised, and annotation-less, model for scene understanding.
181	Multi-channel Correlation Filters	Hamed Kiani Galoogahi, Terence Sim, Simon Lucey	In this paper, we propose a novel framework for learning a multi-channel detector/filter efficiently in the frequency domain, both in terms of training time and memory footprint, which we refer to as a multichannel correlation filter.
182	Image Set Classification Using Holistic Multiple Order Statistics Features and Localized Multi-kernel Metric Learning	Jiwen Lu, Gang Wang, Pierre Moulin	This paper presents a new approach for image set classification, where each training and testing example contains a set of image instances of an object captured from varying viewpoints or under varying illuminations.
183	Modeling Occlusion by Discriminative AND-OR Structures	Bo Li, Wenze Hu, Tianfu Wu, Song-Chun Zhu	Since annotating part occlusion on real images is time-consuming and error-prone, we propose to learn the the AND-OR structure automatically using synthetic images of CAD models placed at different relative positions.
184	Breaking the Chain: Liberation from the Temporal Markov Assumption for Tracking Human Poses	Ryan Tokola, Wongun Choi, Silvio Savarese	We present an approach to multi-target tracking that has expressive potential beyond the capabilities of chainshaped hidden Markov models, yet has significantly reduced complexity.
185	ACTIVE: Activity Concept Transitions in Video Event Classification	Chen Sun, Ram Nevatia	We propose to apply Fisher Kernel techniques so that the concept transitions over time can be encoded into a compact and fixed length feature vector very efficiently.
186	A Joint Intensity and Depth Co-sparse Analysis Model for Depth Map Super-resolution	Martin Kiechle, Simon Hawe, Martin Kleinsteuber	To that end, we introduce a bimodal co-sparse analysis model, which is able to capture the interdependency of registered intensity and depth information.
187	Towards Understanding Action Recognition	Hueihan Jhuang, Juergen Gall, Silvia Zuffi, Cordelia Schmid, Michael J. Black	We evaluate current methods using this dataset and systematically replace the output of various algorithms with ground truth.
188	Go-ICP: Solving 3D Registration Efficiently and Globally Optimally	Jiaolong Yang, Hongdong Li, Yunde Jia	This paper provides the very first globally optimal solution to Euclidean registration of two 3D pointsets or two 3D surfaces under the L 2 error.
189	Geometric Registration Based on Distortion Estimation	Wei Zeng, Mayank Goswami, Feng Luo, Xianfeng Gu	In this work, we quantify the effects of boundary variation and non-isometric deformation to conformal mappings, and give the theoretical upper bounds for the distortions of conformal mappings under these two factors.
190	Handwritten Word Spotting with Corrected Attributes	Jon Almazan, Albert Gordo, Alicia Fornes, Ernest Valveny	We propose an approach to multi-writer word spotting, where the goal is to find a query word in a dataset comprised of document images.
191	Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data	Srinath Sridhar, Antti Oulasvirta, Christian Theobalt	We present a novel method that can capture a broad range of articulated hand motions at interactive rates.
192	Network Principles for SfM: Disambiguating Repeated Structures with Local Context	Kyle Wilson, Noah Snavely	We present a new approach to solving such problems by considering the local visibility structure of such repeated features.
193	Improving Graph Matching via Density Maximization	Chao Wang, Lei Wang, Lingqiao Liu	In this paper, we address these problems with a unified framework–Density Maximization.
194	A Unified Rolling Shutter and Motion Blur Model for 3D Visual Registration	Maxime Meilland, Tom Drummond, Andrew I. Comport	In this paper a complete dense 3D registration model will be derived to account for both motion blur and rolling shutter deformations simultaneously.
195	Fibonacci Exposure Bracketing for High Dynamic Range Imaging	Mohit Gupta, Daisuke Iso, Shree K. Nayar	We present two techniques, one for image capture (Fibonacci exposure bracketing) and one for image registration (generalized registration), to prevent such motion-related artifacts.
196	Potts Model, Parametric Maxflow and K-Submodular Functions	Igor Gridchyn, Vladimir Kolmogorov	One way to tackle this NP-hard problem was proposed by Kovtun [20, 21].
197	Target-Driven Moire Pattern Synthesis by Phase Modulation	Pei-Hen Tsai, Yung-Yu Chuang	This paper investigates an approach for generating two grating images so that the moir??
198	Implied Feedback: Learning Nuances of User Behavior in Image Search	Devi Parikh, Kristen Grauman	We introduce novel features to capitalize on such implied feedback cues, and learn a ranking function that uses them to improve the system’s relevance estimates.
199	How Related Exemplars Help Complex Event Detection in Web Videos?	Yi Yang, Zhigang Ma, Zhongwen Xu, Shuicheng Yan, Alexander G. Hauptmann	To tackle the subjectiveness of human assessment, our algorithm automatically evaluates how positive the related exemplars are for the detection of an event and uses them on an exemplar-specific basis.
200	Decomposing Bag of Words Histograms	Ankit Gandhi, Karteek Alahari, C.V. Jawahar	We aim to decompose a global histogram representation of an image into histograms of its associated objects and regions.
201	Higher Order Matching for Consistent Multiple Target Tracking	Chetan Arora, Amir Globerson	We propose a novel algorithm to find the approximate solution to data assignment problem with higher order temporal constraints using the method of dual decomposition and the MPLP message passing algorithm [21].
202	Complementary Projection Hashing	Zhongming Jin, Yao Hu, Yue Lin, Debing Zhang, Shiding Lin, Deng Cai, Xuelong Li	In this paper, we propose a novel algorithm named Complementary Projection Hashing (CPH) to find the optimal hashing functions which explicitly considers the above two requirements.
203	Super-resolution via Transform-Invariant Group-Sparse Regularization	Carlos Fernandez-Granda, Emmanuel J. Candès	We present a framework to super-resolve planar regions found in urban scenes and other man-made environments by taking into account their 3D geometry.
204	Inferring “Dark Matter” and “Dark Energy” from Videos	Dan Xie, Sinisa Todorovic, Song-Chun Zhu	This paper presents an approach to localizing functional objects in surveillance videos without domain knowledge about semantic object classes that may appear in the scene.
205	Optimal Orthogonal Basis and Image Assimilation: Motion Modeling	Etienne Huot, Giuseppe Papari, Isabelle Herlin	This paper describes modeling and numerical computation of orthogonal bases, which are used to describe images and motion fields.
206	Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going?	Olga Russakovsky, Jia Deng, Zhiheng Huang, Alexander C. Berg, Li Fei-Fei	In this paper we strive to answer two key questions.
207	Neighbor-to-Neighbor Search for Fast Coding of Feature Vectors	Nakamasa Inoue, Koichi Shinoda	This paper proposes a fast computation method, Neighbor-toNeighbor (NTN) search, for this code assignment.
208	Flattening Supervoxel Hierarchies by the Uniform Entropy Slice	Chenliang Xu, Spencer Whitt, Jason J. Corso	In this paper, we propose the first method to overcome this limitation and flatten the hierarchy into a single segmentation.
209	Find the Best Path: An Efficient and Accurate Classifier for Image Hierarchies	Min Sun, Wan Huang, Silvio Savarese	In this work, we propose a classifier which achieves a better trade-off between efficiency and accuracy with a given tree-shaped hierarchy.
210	Model Recommendation with Virtual Probes for Egocentric Hand Detection	Cheng Li, Kris M. Kitani	To address this limitation, we propose the use of virtual probes which can be automatically extracted from the test distribution.
211	Video Motion for Every Visible Point	Susanna Ricco, Carlo Tomasi	Instead, we solve for entire paths directly, and flag the frames in which each is visible.
212	Camera Alignment Using Trajectory Intersections in Unsynchronized Videos	Thomas Kuo, Santhoshkumar Sunderrajan, B.S. Manjunath	To find these intersections, we introduce a novel trajectory matching algorithm based on matching Spatio-Temporal Context Graphs (STCGs).
213	A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis	Fabio Galasso, Naveen Shankar Nagaraja, Tatiana Jimenez Cardenas, Thomas Brox, Bernt Schiele	In this work we provide such an analysis based on annotations of a large video dataset, where each video is manually segmented by multiple persons.
214	Optical Flow via Locally Adaptive Fusion of Complementary Data Costs	Tae Hyun Kim, Hee Seok Lee, Kyoung Mu Lee	In this paper, in contrast to the conventional optical flow framework that uses a single or fixed data model, we study a novel framework that employs locally varying data term that adaptively combines different multiple types of data models.
215	Shortest Paths with Curvature and Torsion	Petter Strandmark, Johannes Ulen, Fredrik Kahl, Leo Grady	This paper describes a method of finding thin, elongated structures in images and volumes.
216	Multi-view 3D Reconstruction from Uncalibrated Radially-Symmetric Cameras	Jae-Hak Kim, Yuchao Dai, Hongdong Li, Xin Du, Jonghyuk Kim	We present a new multi-view 3D Euclidean reconstruction method for arbitrary uncalibrated radially-symmetric cameras, which needs no calibration or any camera model parameters other than radial symmetry.
217	Illuminant Chromaticity from Image Sequences	Veronique Prinet, Dani Lischinski, Michael Werman	Our aim is to leverage information provided by the temporal acquisition, where either the objects or the camera or the light source are/is in motion in order to estimate illuminant color without the need for user interaction or using strong assumptions and heuristics.
218	Allocentric Pose Estimation	M. Jose Antonio, Luc De Raedt, Tinne Tuytelaars	In this paper, we explore how information from other objects in the scene can be exploited for pose estimation.
219	The Interestingness of Images	Michael Gygli, Helmut Grabner, Hayko Riemenschneider, Fabian Nater, Luc Van Gool	We introduce a set of features computationally capturing the three main aspects of visual interestingness that we propose and build an interestingness predictor from them.
220	Learning Maximum Margin Temporal Warping for Action Recognition	Jiang Wang, Ying Wu	To address this challenge, this paper proposes a novel discriminative learning-based temporal alignment method, called maximum margin temporal warping (MMTW), to align two action sequences and measure their matching score.
221	Rolling Shutter Stereo	Olivier Saurer, Kevin Koser, Jean-Yves Bouguet, Marc Pollefeys	In contrast, we analyse the case of significant camera motion, e.g. where a bypassing streetlevel capture vehicle uses a rolling shutter camera in a 3D reconstruction framework.
222	Fast Sparsity-Based Orthogonal Dictionary Learning for Image Restoration	Chenglong Bao, Jian-Feng Cai, Hui Ji	This paper proposed a fast orthogonal dictionary learning method for sparse image representation.
223	Slice Sampling Particle Belief Propagation	Oliver Muller, Michael Ying Yang, Bodo Rosenhahn	We propose to avoid dependence on a proposal distribution by introducing a slice sampling based PBP algorithm.
224	Training Deformable Part Models with Decorrelated Features	Ross Girshick, Jitendra Malik	In this paper, we show how to train a deformable part model (DPM) fast–typically in less than 20 minutes, or four times faster than the current fastest method–while maintaining high average precision on the PASCAL VOC datasets.
225	Efficient Salient Region Detection with Soft Image Abstraction	Ming-Ming Cheng, Jonathan Warrell, Wen-Yan Lin, Shuai Zheng, Vibhav Vineet, Nigel Crook	We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation.
226	Video Segmentation by Tracking Many Figure-Ground Segments	Fuxin Li, Taeyoung Kim, Ahmad Humayun, David Tsai, James M. Rehg	We propose an unsupervised video segmentation approach by simultaneously tracking multiple holistic figureground segments.
227	Bayesian 3D Tracking from Monocular Video	Ernesto Brau, Jinyan Guan, Kyle Simek, Luca Del Pero, Colin Reimer Dawson, Kobus Barnard	We pose the problem in the context of data association, in which observations are assigned to tracks.
228	Concurrent Action Detection with Structural Prediction	Ping Wei, Nanning Zheng, Yibiao Zhao, Song-Chun Zhu	This paper proposes a concurrent action detection model where the action detection is formulated as a structural prediction problem.
229	Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach	Reyes Rios-Cabrera, Tinne Tuytelaars	In this paper we propose a new method for detecting multiple specific 3D objects in real time. Moreover, we propose a challenging new dataset made of 12 objects, for future competing methods on monocular color images.
230	The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection	Mihai Zanfir, Marius Leordeanu, Cristian Sminchisescu	In this paper we propose a fast, simple, yet powerful non-parametric Moving Pose (MP) framework for low-latency human action and activity recognition.
231	Learning a Dictionary of Shape Epitomes with Applications to Image Labeling	Liang-Chieh Chen, George Papandreou, Alan L. Yuille	The first main contribution of this paper is a novel method for representing images based on a dictionary of shape epitomes.
232	Online Motion Segmentation Using Dynamic Label Propagation	Ali Elqursh, Ahmed Elgammal	In this paper, we formulate the problem of motion segmentation as that of manifold separation.
233	Sequential Bayesian Model Update under Structured Scene Prior for Semantic Road Scenes Labeling	Evgeny Levinkov, Mario Fritz	We propose a novel approach that can operate in such conditions and is based on a sequential Bayesian model update in order to robustly integrate the arriving images into the adapting procedure.
234	Directed Acyclic Graph Kernels for Action Recognition	Ling Wang, Hichem Sahbi	In this paper, we address this issue and we propose an alternative action recognition method based on a novel graph kernel.
235	Strong Appearance and Expressive Spatial Models for Human Pose Estimation	Leonid Pishchulin, Mykhaylo Andriluka, Peter Gehler, Bernt Schiele	Typical approaches to articulated pose estimation combine spatial modelling of the human body with appearance modelling of body parts.
236	Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees	Oisin Mac Aodha, Gabriel J. Brostow	We propose a novel example dependent cost-sensitive impurity measure for decision trees.
237	Matching Dry to Wet Materials	Yaser Yacoob	In this paper we investigate the problem of determining if a wet/dry relationship between two image patches explains the differences in their visual appearance.
238	On the Mean Curvature Flow on Graphs with Applications in Image and Manifold Processing	Abdallah El Chakik, Abderrahim Elmoataz, Ahcene Sadi	In this paper, we propose an adaptation and transcription of the mean curvature level set equation on a general discrete domain (weighted graphs with arbitrary topology).
239	Example-Based Facade Texture Synthesis	Dengxin Dai, Hayko Riemenschneider, Gerhard Schmitt, Luc Van Gool	We present a method for synthesizing complex, photo-realistic facade images, from a single example.
240	SYM-FISH: A Symmetry-Aware Flip Invariant Sketch Histogram Shape Descriptor	Xiaochun Cao, Hua Zhang, Si Liu, Xiaojie Guo, Liang Lin	In this paper, we propose a new descriptor, namely Symmetric-aware Flip Invariant Sketch Histogram (SYM-FISH) to refine the shape context feature.
241	Robust Feature Set Matching for Partial Face Recognition	Renliang Weng, Jiwen Lu, Junlin Hu, Gao Yang, Yap-Peng Tan	In this paper, we propose a new partial face recognition approach by using feature set matching, which is able to align partial face patches to holistic gallery faces automatically and is robust to occlusions and illumination changes.
242	Cross-View Action Recognition over Heterogeneous Feature Spaces	Xinxiao Wu, Han Wang, Cuiwei Liu, Yunde Jia	In this paper, we address the problem of transferring action models learned in one view (source view) to another different view (target view), where action instances from these two views are represented by heterogeneous features.
243	Building Part-Based Object Detectors via 3D Geometry	Abhinav Shrivastava, Abhinav Gupta	We propose to learn this geometrydriven deformable part-based model (gDPM) from a set of labeled RGBD images.
244	Active Visual Recognition with Expertise Estimation in Crowdsourcing	Chengjiang Long, Gang Hua, Ashish Kapoor	We present a noise resilient probabilistic model for active learning of a Gaussian process classifier from crowds, i.e., a set of noisy labelers.
245	Attribute Pivots for Guiding Relevance Feedback in Image Search	Adriana Kovashka, Kristen Grauman	To address these drawbacks, we propose to actively select “pivot” exemplars for which feedback in the form of a visual comparison will most reduce the system’s uncertainty.
246	Initialization-Insensitive Visual Tracking through Voting with Salient Local Features	Kwang Moo Yi, Hawook Jeong, Byeongho Heo, Hyung Jin Chang, Jin Young Choi	In this paper we propose an object tracking method in case of inaccurate initializations.
247	Refractive Structure-from-Motion on Underwater Images	Anne Jordt-Sedlazeck, Reinhard Koch	Therefore, in this paper, we propose a system for computing camera path and 3D points with explicit incorporation of refraction using new methods for pose estimation.
248	Semi-dense Visual Odometry for a Monocular Camera	Jakob Engel, Jurgen Sturm, Daniel Cremers	We propose a fundamentally novel approach to real-time visual odometry for a monocular camera.
249	Characterizing Layouts of Outdoor Scenes Using Spatial Topic Processes	Dahua Lin, Jianxiong Xiao	In this paper, we develop a generative model to describe the layouts of outdoor scenes the spatial configuration of regions.
250	A Deformable Mixture Parsing Model with Parselets	Jian Dong, Qiang Chen, Wei Xia, Zhongyang Huang, Shuicheng Yan	In this work, we address the problem of human parsing, namely partitioning the human body into semantic regions, by using the novel Parselet representation.
251	Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution	Mehrtash Harandi, Conrad Sanderson, Chunhua Shen, Brian C. Lovell	In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds.
252	Real-Time Articulated Hand Pose Estimation Using Semi-supervised Transductive Regression Forests	Danhang Tang, Tsz-Ho Yu, Tae-Kyun Kim	This paper presents the first semi-supervised transductive algorithm for real-time articulated hand pose estimation.
253	Face Recognition Using Face Patch Networks	Chaochao Lu, Deli Zhao, Xiaoou Tang	To address this issue, we develop a novel face patch network, based on which we define a new similarity measure called the random path (RP) measure.
254	Depth from Combining Defocus and Correspondence Using Light-Field Cameras	Michael W. Tao, Sunil Hadap, Jitendra Malik, Ravi Ramamoorthi	In this paper, we present a novel simple and principled algorithm that computes dense depth estimation by combining both defocus and correspondence depth cues.
255	Minimal Basis Facility Location for Subspace Segmentation	Choon-Meng Lee, Loong-Fah Cheong	We propose the use of affinity propagation based method to determine the number of motion.
256	Unsupervised Random Forest Manifold Alignment for Lipreading	Yuru Pei, Tae-Kyun Kim, Hongbin Zha	In this paper, we address an efficient lipreading approach by investigating the unsupervised random forest manifold alignment (RFMA).
257	Visual Reranking through Weakly Supervised Multi-graph Learning	Cheng Deng, Rongrong Ji, Wei Liu, Dacheng Tao, Xinbo Gao	This paper proposes a novel image reranking approach by introducing a Co-Regularized Multi-Graph Learning (Co-RMGL) framework, in which the intra-graph and inter-graph constraints are simultaneously imposed to encode affinities in a single graph and consistency across different graphs.
258	Volumetric Semantic Segmentation Using Pyramid Context Features	Jonathan T. Barron, Mark D. Biggin, Pablo Arbelaez, David W. Knowles, Soile V.E. Keranen, Jitendra Malik	We present an algorithm for the per-voxel semantic segmentation of a three-dimensional volume.
259	Transfer Feature Learning with Joint Distribution Adaptation	Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu	In this paper, we put forward a novel transfer learning approach, referred to as Joint Distribution Adaptation (JDA).
260	A Novel Earth Mover’s Distance Methodology for Image Matching with Gaussian Mixture Models	Peihua Li, Qilong Wang, Lei Zhang	To address this problem, we propose a novel EMD methodology for GMM matching.
261	Proportion Priors for Image Sequence Segmentation	Claudia Nieuwenhuis, Evgeny Strekalovskiy, Daniel Cremers	We propose a convex multilabel framework for image sequence segmentation which allows to impose proportion priors on object parts in order to preserve their size ratios across multiple images.
262	Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion	Pierre Moulon, Pascal Monasse, Renaud Marlet	We propose a new global calibration approach based on the fusion of relative motions between image pairs.
263	Complex 3D General Object Reconstruction from Line Drawings	Linjie Yang, Jianzhuang Liu, Xiaoou Tang	In this paper, we propose a novel approach to 3D reconstruction of complex general objects, including manifolds, non-manifold solids, and non-solids.
264	From Large Scale Image Categorization to Entry-Level Categories	Vicente Ordonez, Jia Deng, Yejin Choi, Alexander C. Berg, Tamara L. Berg	In this paper we study entrylevel categories at a large scale and learn the first models for predicting entry-level categories for images.
265	Deterministic Fitting of Multiple Structures Using Iterative MaxFS with Inlier Scale Estimation	Kwang Hee Lee, Sang Wook Lee	We present an efficient deterministic hypothesis generation algorithm for robust fitting of multiple structures based on the maximum feasible subsystem (MaxFS) framework.
266	Efficient and Robust Large-Scale Rotation Averaging	Avishek Chatterjee, Venu Madhav Govindu	In this paper we address the problem of robust and efficient averaging of relative 3D rotations.
267	Automatic Registration of RGB-D Scans via Salient Directions	Bernhard Zeisl, Kevin Koser, Marc Pollefeys	We utilize the principle of salient directions present in the geometry and propose to extract (several) directions from the distribution of surface normals or other cues such as observable symmetries.
268	Video Co-segmentation for Meaningful Action Extraction	Jiaming Guo, Zhuwen Li, Loong-Fah Cheong, Steven Zhiying Zhou	Given a pair of videos having a common action, our goal is to simultaneously segment this pair of videos to extract this common action. To evaluate the performance of our framework, we introduce a dataset containing clips that have animal actions as well as human actions.
269	Coherent Motion Segmentation in Moving Camera Videos Using Optical Flow Orientations	Manjunath Narayana, Allen Hanson, Erik Learned-Miller	We introduce a probabilistic model that automatically estimates the number of observed independent motions and results in a labeling that is consistent with real-world motion in the scene.
270	Live Metric 3D Reconstruction on Mobile Phones	Petri Tanskanen, Kalin Kolev, Lorenz Meier, Federico Camposeco, Olivier Saurer, Marc Pollefeys	In this paper, we propose a complete on-device 3D reconstruction pipeline for mobile monocular hand-held devices, which generates dense 3D models with absolute scale on-site while simultaneously supplying the user with real-time interactive feedback.
271	Dynamic Structured Model Selection	David Weiss, Benjamin Sapp, Ben Taskar	In this work, we propose a novel two-tier architecture that provides dynamic speed/accuracy trade-offs through a simple type of introspection.
272	Ensemble Projection for Semi-supervised Image Classification	Dengxin Dai, Luc Van Gool	This paper investigates the problem of semi-supervised classification.
273	Saliency Detection in Large Point Sets	Elizabeth Shtrom, George Leifman, Ayellet Tal	In this paper we present an algorithm for detecting the salient points in unorganized 3D point sets.
274	Segmentation Driven Object Detection with Fisher Vectors	Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid	We present an object detection system based on the Fisher vector (FV) image representation computed over SIFT and color descriptors.
275	Joint Segmentation and Pose Tracking of Human in Natural Videos	Taegyu Lim, Seunghoon Hong, Bohyung Han, Joon Hee Han	We propose an on-line algorithm to extract a human by foreground/background segmentation and estimate pose of the human from the videos captured by moving cameras.
276	NYC3DCars: A Dataset of 3D Vehicles in Geographic Context	Kevin Matzen, Noah Snavely	To aid in studying connections between geometry and recognition, we introduce NYC3DCars, a rich dataset for vehicle detection in urban scenes built from Internet photos drawn from the wild, focused on densely trafficked areas of New York City.
277	Robust Trajectory Clustering for Motion Segmentation	Feng Shi, Zhong Zhou, Jiangjian Xiao, Wei Wu	In this paper, we present an approach that exploits temporal and spatial characteristics from tracked points to facilitate segmentation of incomplete and corrupted trajectories, thereby obtain highly robust results against severe data missing and noises.
278	Active Learning of an Action Detector from Untrimmed Videos	Sunil Bandla, Kristen Grauman	We propose a method to actively request the most useful video annotations among a large set of unlabeled videos.
279	YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition	Sergio Guadarrama, Niveda Krishnamoorthy, Girish Malkarnenkar, Subhashini Venugopalan, Raymond Mooney, Trevor Darrell, Kate Saenko	In this paper, we tackle the challenge of recognizing and describing activities “in-the-wild”.
280	Manifold Based Face Synthesis from Sparse Samples	Hongteng Xu, Hongyuan Zha	Specifically, we propose methods based on generating auxiliary data in the form of synthetic samples using transformations of the original sparse samples.
281	Like Father, Like Son: Facial Expression Dynamics for Kinship Verification	Hamdi Dibeklioglu, Albert Ali Salah, Theo Gevers	This paper explores the possibility of employing facial expression dynamics in this problem.
282	Toward Guaranteed Illumination Models for Non-convex Objects	Yuqian Zhang, Cun Mu, Han-Wen Kuo, John Wright	As the number of such images required for guaranteed verification may be large, we introduce a new formulation for cone preserving dimensionality reduction, which leverages tools from sparse and low-rank decomposition to reduce the complexity, while controlling the approximation error with respect to the original model.
283	Nonparametric Blind Super-resolution	Tomer Michaeli, Michal Irani	We propose a general framework for “blind” super resolution.
284	Pedestrian Parsing via Deep Decompositional Network	Ping Luo, Xiaogang Wang, Xiaoou Tang	We propose a new Deep Decompositional Network (DDN) for parsing pedestrian images into semantic regions, such as hair, head, body, arms, and legs, where the pedestrians can be heavily occluded.
285	Large-Scale Video Hashing via Structure Learning	Guangnan Ye, Dong Liu, Jun Wang, Shih-Fu Chang	In this paper, we propose a supervised method that explores the structure learning techniques to design efficient hash functions.
286	Salient Region Detection by UFO: Uniqueness, Focusness and Objectness	Peng Jiang, Haibin Ling, Jingyi Yu, Jingliang Peng	In this paper we propose a novel salient region detection algorithm by integrating three important visual cues namely uniqueness, focusness and objectness (UFO).
287	Revisiting the PnP Problem: A Fast, General and Optimal Solution	Yinqiang Zheng, Yubin Kuang, Shigeki Sugimoto, Kalle Astrom, Masatoshi Okutomi	In this paper, we revisit the classical perspective-n-point (PnP) problem, and propose the first non-iterative O(n) solution that is fast, generally applicable and globally optimal.
288	Rectangling Stereographic Projection for Wide-Angle Image Visualization	Che-Han Chang, Min-Chun Hu, Wen-Huang Cheng, Yung-Yu Chuang	This paper proposes a new projection model for mapping a hemisphere to a plane.
289	Hidden Factor Analysis for Age Invariant Face Recognition	Dihong Gong, Zhifeng Li, Dahua Lin, Jianzhuang Liu, Xiaoou Tang	Specifically, we propose a new method, called Hidden Factor Analysis (HFA).
290	Randomized Ensemble Tracking	Qinxun Bai, Zheng Wu, Stan Sclaroff, Margrit Betke, Camille Monnier	We propose a randomized ensemble algorithm to model the time-varying appearance of an object for visual tracking.
291	Motion-Aware KNN Laplacian for Video Matting	Dingzeyu Li, Qifeng Chen, Chi-Keung Tang	This paper demonstrates how the nonlocal principle benefits video matting via the KNN Laplacian, which comes with a straightforward implementation using motionaware K nearest neighbors.
292	Pose-Configurable Generic Tracking of Elongated Objects	Daniel Wesierski, Patrick Horain	We describe a unified, configurable framework for tracking the pose of elongated objects, which move in the image plane and extend over the image region.
293	Heterogeneous Auto-similarities of Characteristics (HASC): Exploiting Relational Information for Classification	Marco San Biagio, Marco Crocco, Marco Cristani, Samuele Martelli, Vittorio Murino	In this paper, we embed this principle in a novel image descriptor, dubbed Heterogeneous Auto-Similarities of Characteristics (HASC).
294	A Learning-Based Approach to Reduce JPEG Artifacts in Image Matting	Inchang Choi, Sunyeong Kim, Michael S. Brown, Yu-Wing Tai	To address this situation, we propose a learning-based post-processing method to improve the alpha mattes extracted from JPEG images.
295	Content-Aware Rotation	Kaiming He, Huiwen Chang, Jian Sun	Instead of doing rigid rotation, we propose a warping method that creates the perception of rotation and avoids cropping.
296	Perspective Motion Segmentation via Collaborative Clustering	Zhuwen Li, Jiaming Guo, Loong-Fah Cheong, Steven Zhiying Zhou	For model selection, we propose an over-segment and merge approach, where the merging step is based on the property of the 1 -norm of the mutual sparse representation of two oversegmented groups.
297	Progressive Multigrid Eigensolvers for Multiscale Spectral Segmentation	Michael Maire, Stella X. Yu	We make a significant algorithmic advance in the form of a custom multigrid eigensolver for constrained Angular Embedding problems possessing coarseto-fine structure.
298	Shape Index Descriptors Applied to Texture-Based Galaxy Analysis	Kim Steenstrup Pedersen, Kristoffer Stensbo-Smidt, Andrew Zirm, Christian Igel	In this study, we build a regression model for predicting a spectroscopic quantity, the specific star-formation rate (sSFR).
299	Markov Network-Based Unified Classifier for Face Identification	Wonjun Hwang, Kyungshik Roh, Junmo Kim	We propose a novel unifying framework using a Markov network to learn the relationship between multiple classifiers in face recognition. For each observation-hidden node pair, we collect a set of gallery candidates that are most similar to the observation instance, and the relationship between the hidden nodes is captured in terms of the similarity matrix between the collected gallery images.
300	Learning Hash Codes with Listwise Supervision	Jun Wang, Wei Liu, Andy X. Sun, Yu-Gang Jiang	In this paper, we propose to leverage listwise supervision into a principled hash function learning framework.
301	A Robust Analytical Solution to Isometric Shape-from-Template with Focal Length Calibration	Adrien Bartoli, Daniel Pizarro, Toby Collins	We study the uncalibrated isometric Shape-fromTemplate problem, that consists in estimating an isometric deformation from a template shape to an input image whose focal length is unknown.
302	Real-World Normal Map Capture for Nearly Flat Reflective Surfaces	Bastien Jacquet, Christian Hane, Kevin Koser, Marc Pollefeys	In this work, we present a practical approach to capturing normal maps in real-world scenes using video only.
303	Perceptual Fidelity Aware Mean Squared Error	Wufeng Xue, Xuanqin Mou, Lei Zhang, Xiangchu Feng	In this paper we propose a simple framework to enhance the perceptual fidelity awareness of MSE by introducing an l 2 -norm structural error term to it.
304	Temporally Consistent Superpixels	Matthias Reso, Jorn Jachalsky, Bodo Rosenhahn, Jorn Ostermann	In this regards, this paper presents a highly competitive approach for temporally consistent superpixels for video content.
305	Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve	Sakrapee Paisitkriangkrai, Chunhua Shen, Anton Van Den Hengel	We propose a novel ensemble learning method which achieves a maximal detection rate at a user-defined range of false positive rates by directly optimizing the partial AUC using structured learning.
306	Rank Minimization across Appearance and Shape for AAM Ensemble Fitting	Xin Cheng, Sridha Sridharan, Jason Saragih, Simon Lucey	In this paper we look at how these seemingly contrasting factors can complement one another for the problem of AAM fitting of an ensemble of images stemming from a constrained set (e.g. an ensemble of face images of the same person).
307	Random Forests of Local Experts for Pedestrian Detection	Javier Marin, David Vazquez, Antonio M. Lopez, Jaume Amores, Bastian Leibe	In this paper, we propose a pedestrian detection method that efficiently combines multiple local experts by means of a Random Forest ensemble.
308	Monocular Image 3D Human Pose Estimation under Self-Occlusion	Ibrahim Radwan, Abhinav Dhall, Roland Goecke	In this paper, an automatic approach for 3D pose reconstruction from a single image is proposed.
309	Constructing Adaptive Complex Cells for Robust Visual Tracking	Dapeng Chen, Zejian Yuan, Yang Wu, Geng Zhang, Nanning Zheng	In this paper we present that, besides the two paradigms, the composition of local region histograms can also provide diverse and important object cues.
310	Mining Motion Atoms and Phrases for Complex Action Recognition	Limin Wang, Yu Qiao, Xiaoou Tang	We introduce a bottom-up phrase construction algorithm and a greedy selection method for this mining task.
311	Video Event Understanding Using Natural Language Descriptions	Vignesh Ramanathan, Percy Liang, Li Fei-Fei	In this work, we propose a method to learn such models based on natural language descriptions of the training videos, which are easier to collect and scale with the number of actions and roles.
312	Human Re-identification by Matching Compositional Template with Cluster Sampling	Yuanlu Xu, Liang Lin, Wei-Shi Zheng, Xiaobai Liu	This paper aims at a newly raising task in visual surveillance: re-identifying people at a distance by matching body information, given several reference examples.
313	Estimating the Material Properties of Fabric from Video	Katherine L. Bouman, Bei Xiao, Peter Battaglia, William T. Freeman	We present a framework to automatically analyze videos of fabrics moving under various unknown wind forces, and recover two key material properties of the fabric: stiffness and area weight.
314	An Adaptive Descriptor Design for Object Recognition in the Wild	Zhenyu Guo, Z. Jane Wang	In this paper, we investigate the influence of picture styles on object recognition by making a connection between image descriptors and a pixel mapping function g, and accordingly propose an adaptive approach based on a g-incorporated kernel descriptor and multiple kernel learning, without estimating or specifying the image styles used in training and testing.
315	Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision	Tae-Hyun Oh, Hyeongwoo Kim, Yu-Wing Tai, Jean-Charles Bazin, In So Kweon	In this paper, instead of minimizing the nuclear norm, we propose to minimize the partial sum of singular values.
316	Semantically-Based Human Scanpath Estimation with HMMs	Huiying Liu, Dong Xu, Qingming Huang, Wen Li, Min Xu, Stephen Lin	We present a method for estimating human scanpaths, which are sequences of gaze shifts that follow visual attention over an image.
317	From Semi-supervised to Transfer Counting of Crowds	Chen Change Loy, Shaogang Gong, Tao Xiang	In this study, we propose to address this problem from three perspectives: (1) Instead of exhaustively annotating every single frame, the most informative frames are selected for annotation automatically and actively.
318	Enhanced Continuous Tabu Search for Parameter Estimation in Multiview Geometry	Guoqing Zhou, Qing Wang	In the paper, we propose a novel approach under the framework of enhanced continuous tabu search (ECTS) for generic parameter estimation in multiview geometry.
319	3D Sub-query Expansion for Improving Sketch-Based Multi-view Image Retrieval	Yen-Liang Lin, Cheng-Yu Huang, Hao-Jeng Wang, Winston Hsu	We propose a 3D sub-query expansion approach for boosting sketch-based multi-view image retrieval.
320	Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines	Shuran Song, Jianxiong Xiao	In this paper, we construct a unified benchmark dataset of 100 RGBD videos with high diversity, propose different kinds of RGBD tracking algorithms using 2D or 3D model, and present a quantitative comparison of various algorithms with RGB or RGBD input.
321	Modeling Self-Occlusions in Dynamic Shape and Appearance Tracking	Yanchao Yang, Ganesh Sundaramoorthi	We present a method to track the precise shape of a dynamic object in video.
322	Fingerspelling Recognition with Semi-Markov Conditional Random Fields	Taehwan Kim, Greg Shakhnarovich, Karen Livescu	In this paper we investigate the case of fingerspelling recognition, which can be very challenging due to the quick, small motions of the fingers.
323	Attribute Dominance: What Pops Out?	Naman Turakhia, Devi Parikh	In this paper we tap into this information by modeling attribute dominance.
324	Modifying the Memorability of Face Photographs	Aditya Khosla, Wilma A. Bainbridge, Antonio Torralba, Aude Oliva	Here, we provide a method to modify the memorability of individual face photographs, while keeping the identity and other facial traits (e.g. age, attractiveness, and emotional magnitude) of the individual fixed.
325	A Fully Hierarchical Approach for Finding Correspondences in Non-rigid Shapes	Ivan Sipiran, Benjamin Bustos	This paper presents a hierarchical method for finding correspondences in non-rigid shapes.
326	Fast Direct Super-Resolution by Simple Functions	Chih-Yuan Yang, Ming-Hsuan Yang	In this paper, we propose to split the feature space into numerous subspaces and collect exemplars to learn priors for each subspace, thereby creating effective mapping functions.
327	Tree Shape Priors with Connectivity Constraints Using Convex Relaxation on General Graphs	Jan Stuhmer, Peter Schroder, Daniel Cremers	We propose a novel method to include a connectivity prior into image segmentation that is based on a binary labeling of a directed graph, in this case a geodesic shortest path tree.
328	Learning the Visual Interpretation of Sentences	C. L. Zitnick, Devi Parikh, Lucy Vanderwende	In this paper we learn the visual features that correspond to semantic phrases derived from sentences.
329	A Unified Probabilistic Approach Modeling Relationships between Attributes and Objects	Xiaoyang Wang, Qiang Ji	This paper proposes a unified probabilistic model to model the relationships between attributes and objects for attribute prediction and object recognition.
330	Domain Transfer Support Vector Ranking for Person Re-identification without Target Camera Label Information	Andy J. Ma, Pong C. Yuen, Jiawei Li	Given the matched (positive) and unmatched (negative) image pairs from source domain cameras, as well as unmatched (negative) image pairs which can be easily generated from target domain cameras, we propose a Domain Transfer Ranked Support Vector Machines (DTRSVM) method for re-identification under target domain cameras.
331	Sparse Variation Dictionary Learning for Face Recognition with a Single Training Sample per Person	Meng Yang, Luc Van Gool, Lei Zhang	To address this issue, in this paper we learn a sparse variation dictionary from a generic training set to improve the query sample representation by STSPP.
332	Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors	Jian Zhang, Chen Kan, Alexander G. Schwing, Raquel Urtasun	In this paper we propose an approach to jointly estimate the layout of rooms as well as the clutter present in the scene using RGB-D data.
333	Learning to Share Latent Tasks for Action Recognition	Qiang Zhou, Gang Wang, Kui Jia, Qi Zhao	In this paper, we investigate knowledge sharing across categories for action recognition in videos.
334	Space-Time Robust Representation for Action Recognition	Nicolas Ballas, Yi Yang, Zhen-Zhong Lan, Bertrand Delezoide, Francoise Preteux, Alexander Hauptmann	We propose a novel content driven pooling that leverages space-time context while being robust toward global space-time transformations.
335	Street View Motion-from-Structure-from-Motion	Bryan Klingner, David Martin, James Roseborough	We describe a structure-from-motion framework that handles “generalized” cameras, such as moving rollingshutter cameras, and works at an unprecedented scale-billions of images covering millions of linear kilometers of roads–by exploiting a good relative pose prior along vehicle paths.
336	Quantize and Conquer: A Dimensionality-Recursive Solution to Clustering, Vector Quantization, and Image Retrieval	Yannis Avrithis	Inspired by the close relation between nearest neighbor search and clustering in high-dimensional spaces as well as the success of one helping to solve the other, we introduce a new paradigm where both problems are solved simultaneously.
337	Dynamic Pooling for Complex Event Recognition	Weixin Li, Qian Yu, Ajay Divakaran, Nuno Vasconcelos	A dynamic pooling operator is defined so as to enable a unified solution to the problems of event specific video segmentation, temporal structure modeling, and event detection.
338	A Practical Transfer Learning Algorithm for Face Verification	Xudong Cao, David Wipf, Fang Wen, Genquan Duan, Jian Sun	Herein we propose a principled transfer learning approach for merging plentiful source-domain data with limited samples from some target domain of interest to create a classifier that ideally performs nearly as well as if rich target-domain data were present.
339	Incorporating Cloud Distribution in Sky Representation	Kuan-Chuan Peng, Tsuhan Chen	Most sky models only describe the cloudiness of the overall sky by a single category or parameter such as sky index, which does not account for the distribution of the clouds across the sky.
340	From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding	Weiyu Zhang, Menglong Zhu, Konstantinos G. Derpanis	This paper presents a novel approach for analyzing human actions in non-scripted, unconstrained video settings based on volumetric, x-y-t, patch classifiers, termed actemes.
341	Distributed Low-Rank Subspace Segmentation	Ameet Talwalkar, Lester Mackey, Yadong Mu, Shih-Fu Chang, Michael I. Jordan	In this work, we propose a novel divide-and-conquer algorithm for large-scale subspace segmentation that can cope with LRR’s non-decomposable constraints and maintains LRR’s strong recovery guarantees.
342	Modeling 4D Human-Object Interactions for Event and Object Recognition	Ping Wei, Yibiao Zhao, Nanning Zheng, Song-Chun Zhu	In this paper, we propose a 4D human-object interaction model, where the two tasks jointly boost each other. For evaluation, we built a large-scale multiview 3D event dataset which contains 3815 video sequences and 383,036 RGBD frames captured by the Kinect cameras.
343	Codemaps – Segment, Classify and Search Objects Locally	Zhenyang Li, Efstratios Gavves, Koen E.A. van de Sande, Cees G.M. Snoek, Arnold W.M. Smeulders	In this paper we aim for segmentation and classification of objects.
344	Bounded Labeling Function for Global Segmentation of Multi-part Objects with Geometric Constraints	Masoud S. Nosrati, Shawn Andrews, Ghassan Hamarneh	In this paper, we augment the popular MumfordShah model to incorporate two important geometrical constraints, termed containment and detachment, between different regions with a specified minimum distance between their boundaries.
345	Recognizing Text with Perspective Distortion in Natural Scenes	Trung Quy Phan, Palaiahnakote Shivakumara, Shangxuan Tian, Chew Lim Tan	This paper presents an approach to text recognition in natural scene images. Furthermore, we introduce a new dataset called StreetViewText-Perspective, which contains texts in street images with a great variety of viewpoints.
346	Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition	Ricardo Cabral, Fernando De La Torre, Joao P. Costeira, Alexandre Bernardino	This paper proposes a unified approach to bilinear factorization and nuclear norm regularization, that inherits the benefits of both.
347	Efficient 3D Scene Labeling Using Fields of Trees	Olaf Kahler, Ian Reid	We address the problem of 3D scene labeling in a structured learning framework.
348	Efficient Hand Pose Estimation from a Single Depth Image	Chi Xu, Li Cheng	A dedicated three-step pipeline is proposed: Initial estimation step provides an initial estimation of the hand in-plane orientation and 3D location; Candidate generation step produces a set of 3D pose candidate from the Hough voting space with the help of the rotational invariant depth features; Verification step delivers the final 3D hand pose as the solution to an optimization problem.
349	First-Photon Imaging: Scene Depth and Reflectance Acquisition from One Detected Photon per Pixel	Ahmed Kirmani, Dongeek Shin, Dheera Venkatraman, Franco N. C. Wong, Vivek K Goyal	Our technique enables rapid, low-power, and noise-tolerant active optical imaging.
350	Supervised Binary Hash Code Learning with Jensen Shannon Divergence	Lixin Fan	This paper proposes to learn binary hash codes within a statistical learning framework, in which an upper bound of the probability of Bayes decision errors is derived for different forms of hash functions and a rigorous proof of the convergence of the upper bound is presented.
351	Internet Based Morphable Model	Ira Kemelmacher-Shlizerman	In this paper we present a new concept of building a morphable model directly from photos on the Internet.
352	Curvature-Aware Regularization on Riemannian Submanifolds	Kwang In Kim, James Tompkin, Christian Theobalt	We present a procedure for characterizing the extrinsic (as well as intrinsic) curvature of a manifold M which is described by a sampled point cloud in a high-dimensional Euclidean space.
353	From Subcategories to Visual Composites: A Multi-level Framework for Object Detection	Tian Lan, Michalis Raptis, Leonid Sigal, Greg Mori	We propose a weakly-supervised framework for object detection where we discover subcategories and the composites automatically with only traditional object-level category labels as input.
354	A Generalized Low-Rank Appearance Model for Spatio-temporally Correlated Rain Streaks	Yi-Lei Chen, Chiou-Ting Hsu	In this paper, we propose a novel low-rank appearance model for removing rain streaks.
355	Parallel Transport of Deformations in Shape Space of Elastic Surfaces	Qian Xie, Sebastian Kurtek, Huiling Le, Anuj Srivastava	Using the square-root normal field (SRNF) representation of parameterized surfaces, we present a method for transporting deformations along paths in the shape space.
356	Human Attribute Recognition by Rich Appearance Dictionary	Jungseock Joo, Shuo Wang, Song-Chun Zhu	We present a part-based approach to the problem of human attribute recognition from a single image of a human body.
357	Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation	Zhiyuan Shi, Timothy M. Hospedales, Tao Xiang	We propose a novel framework based on Bayesian joint topic modelling.
358	Frustratingly Easy NBNN Domain Adaptation	Tatiana Tommasi, Barbara Caputo	We build on this result, and present an NBNN-based domain adaptation algorithm that learns iteratively a class metric while inducing, for each sample, a large margin separation among classes.
359	Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition	Joao F. Henriques, Joao Carreira, Rui Caseiro, Jorge Batista	In this paper, we show that the Gram matrix describing such data is block-circulant.
360	Cross-Field Joint Image Restoration via Scale Map	Qiong Yan, Xiaoyong Shen, Li Xu, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Jiaya Jia	We propose a two-image restoration framework considering input images in different fields, for example, one noisy color image and one dark-flashed nearinfrared image.
361	STAR3D: Simultaneous Tracking and Reconstruction of 3D Objects Using RGB-D Data	Carl Yuheng Ren, Victor Prisacariu, David Murray, Ian Reid	We introduce a probabilistic framework for simultaneous tracking and reconstruction of 3D rigid objects using an RGB-D camera.
362	Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery Using Multi-directional Oriented Flux	Engin Turetken, Carlos Becker, Przemyslaw Glowacki, Fethallah Benmansour, Pascal Fua	We propose a new approach to detecting irregular curvilinear structures in noisy image stacks.
363	Learning Slow Features for Behaviour Analysis	Lazaros Zafeiriou, Mihalis A. Nicolaou, Stefanos Zafeiriou, Symeon Nikitidis, Maja Pantic	In this paper, we propose a number of extensions in both the deterministic and the probabilistic SFA optimization frameworks.
364	Multi-view Object Segmentation in Space and Time	Abdelaziz Djelouah, Jean-Sebastien Franco, Edmond Boyer, Francois Le Clerc, Patrick Perez	In this paper, we address the problem of object segmentation in multiple views or videos when two or more viewpoints of the same scene are available.
365	Non-convex P-Norm Projection for Robust Sparsity	Mithun Das Gupta, Sanjeev Kumar	In this paper, we investigate the properties of L p norm (p Ittiswithin a projection framework.
366	Robust Matrix Factorization with Unknown Noise	Deyu Meng, Fernando De La Torre	To address this problem, this paper proposes a low-rank matrix factorization problem with a Mixture of Gaussians (MoG) noise model.
367	A General Two-Step Approach to Learning-Based Hashing	Guosheng Lin, Chunhua Shen, David Suter, Anton van den Hengel	Here we propose a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions.
368	Dynamic Scene Deblurring	Tae Hyun Kim, Byeongjoo Ahn, Kyoung Mu Lee	In this paper, in contrast to this restrictive assumption, we address the deblurring problem of general dynamic scenes which contain multiple moving objects as well as camera shake.
369	Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items	Kota Yamaguchi, M. Hadi Kiapour, Tamara L. Berg	In this paper, we tackle the clothing parsing problem using a retrieval based approach.
370	Deep Learning Identity-Preserving Face Space	Zhenyao Zhu, Ping Luo, Xiaogang Wang, Xiaoou Tang	This paper addresses this challenge by proposing a new learningbased face representation: the face identity-preserving (FIP) features.
371	Predicting Primary Gaze Behavior Using Social Saliency Fields	Hyun Soo Park, Eakta Jain, Yaser Sheikh	We present a method to predict primary gaze behavior in a social scene.
372	A Flexible Scene Representation for 3D Reconstruction Using an RGB-D Camera	Diego Thomas, Akihiro Sugimoto	We propose a new flexible 3D scene representation using a set of planes that is cheap in memory use and, nevertheless, achieves accurate reconstruction of indoor scenes from RGB-D image sequences.
373	Multi-view Normal Field Integration for 3D Reconstruction of Mirroring Objects	Michael Weinmann, Aljosa Osep, Roland Ruiters, Reinhard Klein	In this paper, we present a novel, robust multi-view normal field integration technique for reconstructing the full 3D shape of mirroring objects.
374	Exemplar-Based Graph Matching for Robust Facial Landmark Localization	Feng Zhou, Jonathan Brandt, Zhe Lin	In this paper, we present exemplar-based graph matching (EGM), a robust framework for facial landmark localization.
375	Space-Time Tradeoffs in Photo Sequencing	Tali Dekel (Basha), Yael Moses, Shai Avidan	We propose a geometric based solution, followed by rank aggregation to the photo-sequencing problem.
376	Estimating Human Pose with Flowing Puppets	Silvia Zuffi, Javier Romero, Cordelia Schmid, Michael J. Black	Here we take a different approach based on a simple observation: Information about how a person moves from frame to frame is present in the optical flow field.
377	Action and Event Recognition with Fisher Vectors on a Compact Feature Set	Dan Oneata, Jakob Verbeek, Cordelia Schmid	We present a large and varied set of evaluations, considering (i) classification of short actions in five datasets, (ii) localization of such actions in feature-length movies, and (iii) large-scale recognition of complex events.
378	Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition	Hans Lobel, Rene Vidal, Alvaro Soto	In this work we propose a novel hierarchical approach to visual recognition based on a BoVW scheme that jointly learns suitable midand top-level representations.
379	Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics	Nicolas Riche, Matthieu Duvinage, Matei Mancas, Bernard Gosselin, Thierry Dutoit	In this paper, on human eye fixations ,we compare the ranking of 12 state-of-the art saliency models using 12 similarity metrics.
380	Dynamic Label Propagation for Semi-supervised Multi-class Multi-label Classification	Bo Wang, Zhuowen Tu, John K. Tsotsos	Here, we propose a semi-supervised multi-class/multi-label classification scheme, dynamic label propagation (DLP), which performs transductive learning through propagation in a dynamic process.
381	Learning Discriminative Part Detectors for Image Classification and Cosegmentation	Jian Sun, Jean Ponce	In this paper, we address the problem of learning discriminative part detectors from image sets with category labels.
382	Co-segmentation by Composition	Alon Faktor, Michal Irani	We define ‘good’ co-segments to be ones which can be easily composed (like a puzzle) from large pieces of other co-segments, yet are difficult to compose from remaining image parts.
383	A New Image Quality Metric for Image Auto-denoising	Xiangfei Kong, Kuan Li, Qingxiong Yang, Liu Wenyin, Ming-Hsuan Yang	This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/video denoising algorithms for auto-denoising.
384	Random Faces Guided Sparse Many-to-One Encoder for Pose-Invariant Face Recognition	Yizhe Zhang, Ming Shao, Edward K. Wong, Yun Fu	In this paper, we propose a high-level feature learning scheme to extract pose-invariant identity feature for face recognition.
385	Text Localization in Natural Images Using Stroke Feature Transform and Text Covariance Descriptors	Weilin Huang, Zhe Lin, Jianchao Yang, Jue Wang	In this paper, we present a new approach for text localization in natural images, by discriminating text and non-text regions at three levels: pixel, component and textline levels.
386	Modeling the Calibration Pipeline of the Lytro Camera for High Quality Light-Field Image Reconstruction	Donghyeon Cho, Minhaeng Lee, Sunyeong Kim, Yu-Wing Tai	In this paper, using the Lytro camera as an example, we describe step-by-step procedures to calibrate a raw light-field image.
387	Learning Graph Matching: Oriented to Category Modeling from Cluttered Scenes	Quanshi Zhang, Xuan Song, Xiaowei Shao, Huijing Zhao, Ryosuke Shibasaki	In this paper, we redefine the learning of graph matching as a model learning problem.
388	Action Recognition with Improved Trajectories	Heng Wang, Cordelia Schmid	This paper improves their performance by taking into account camera motion to correct them.
389	A Generic Deformation Model for Dense Non-rigid Surface Registration: A Higher-Order MRF-Based Approach	Yun Zeng, Chaohui Wang, Xianfeng Gu, Dimitris Samaras, Nikos Paragios	We propose a novel approach for dense non-rigid 3D surface registration, which brings together Riemannian geometry and graphical models.
390	Joint Inverted Indexing	Yan Xia, Kaiming He, Fang Wen, Jian Sun	Instead of computing the multiple quantizers independently, we present a method that creates them jointly.
391	From Point to Set: Extend the Learning of Distance Metrics	Pengfei Zhu, Lei Zhang, Wangmeng Zuo, David Zhang	In this paper, we extend the PPD based Mahalanobis distance metric learning to PSD and SSD based ones, namely point-to-set distance metric learning (PSDML) and set-to-set distance metric learning (SSDML), and solve them under a unified optimization framework.
392	Learning View-Invariant Sparse Representations for Cross-View Action Recognition	Jingjing Zheng, Zhuolin Jiang	We present an approach to jointly learn a set of viewspecific dictionaries and a common dictionary for crossview action recognition.
393	Line Assisted Light Field Triangulation and Stereo Matching	Zhan Yu, Xinqing Guo, Haibing Lin, Andrew Lumsdaine, Jingyi Yu	In this paper, we explore geometric structures of 3D lines in ray space for improving light field triangulation and stereo matching.
394	Viewing Real-World Faces in 3D	Tal Hassner	We present a data-driven method for estimating the 3D shapes of faces viewed in single, unconstrained photos (aka “in-the-wild”).
395	Towards Motion Aware Light Field Video for Dynamic Scenes	Salil Tambe, Ashok Veeraraghavan, Amit Agrawal	We present the concept, design and implementation of a LF video camera that allows capturing high resolution LF video.
396	Abnormal Event Detection at 150 FPS in MATLAB	Cewu Lu, Jianping Shi, Jiaya Jia	Based on inherent redundancy of video structures, we propose an efficient sparse combination learning framework.
397	Elastic Fragments for Dense Scene Reconstruction	Qian-Yi Zhou, Stephen Miller, Vladlen Koltun	We present an approach to reconstruction of detailed scene geometry from range video.
398	Shape Anchors for Data-Driven Multi-view Reconstruction	Andrew Owens, Jianxiong Xiao, Antonio Torralba, William Freeman	We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues.
399	Piecewise Rigid Scene Flow	Christoph Vogel, Konrad Schindler, Stefan Roth	To overcome the limitations of existing techniques, we introduce a novel model that represents the dynamic 3D scene by a collection of planar, rigidly moving, local segments.
400	Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing	Amir Sadovnik, Andrew Gallagher, Devi Parikh, Tsuhan Chen	In this work we propose a spoken attribute classifier which models a more natural way of using an attribute in a description.
401	Coupled Dictionary and Feature Space Learning with Applications to Cross-Domain Image Synthesis and Recognition	De-An Huang, Yu-Chiang Frank Wang	In this paper, we propose a unified model for coupled dictionary and feature space learning.
402	Hierarchical Part Matching for Fine-Grained Visual Categorization	Lingxi Xie, Qi Tian, Richang Hong, Shuicheng Yan, Bo Zhang	In this paper, we propose a powerful flowchart named Hierarchical Part Matching (HPM) to cope with finegrained classification tasks.
403	Locally Affine Sparse-to-Dense Matching for Motion and Occlusion Estimation	Marius Leordeanu, Andrei Zanfir, Cristian Sminchisescu	We propose a novel sparse-to-dense matching method for motion field estimation and occlusion detection.
404	SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels	Jianxiong Xiao, Andrew Owens, Antonio Torralba	In this paper, we introduce SUN3D, a large-scale RGB-D video database with camera pose and object labels, capturing the full 3D extent of many places.
405	A Deep Sum-Product Architecture for Robust Facial Attributes Analysis	Ping Luo, Xiaogang Wang, Xiaoou Tang	This challenge is addressed in this paper.
406	Point-Based 3D Reconstruction of Thin Objects	Benjamin Ummenhofer, Thomas Brox	In this paper we present a dense pointbased reconstruction method that can deal with this special class of objects.
407	Structured Learning of Sum-of-Submodular Higher Order Energy Functions	Alexander Fix, Thorsten Joachims, Sung Min Park, Ramin Zabih	In this paper we address the important class of sum-of-submodular (SoS) functions [2, 18], which can be efficiently minimized via a variant of max flow called submodular flow [6].
408	Affine-Constrained Group Sparse Coding and Its Application to Image-Based Classifications	Yu-Tseh Chi, Mohsen Ali, Muhammad Rushdi, Jeffrey Ho	This paper proposes a novel approach for sparse coding that further improves upon the sparse representation-based classification (SRC) framework.
409	Latent Space Sparse Subspace Clustering	Vishal M. Patel, Hien Van Nguyen, Rene Vidal	We propose a novel algorithm called Latent Space Sparse Subspace Clustering for simultaneous dimensionality reduction and clustering of data lying in a union of subspaces.
410	To Aggregate or Not to aggregate: Selective Match Kernels for Image Search	Giorgos Tolias, Yannis Avrithis, Herve Jegou	This paper considers a family of metrics to compare images based on their local descriptors.
411	Person Re-identification by Salience Matching	Rui Zhao, Wanli Ouyang, Xiaogang Wang	In this paper, we exploit the pairwise salience distribution relationship between pedestrian images, and solve the person re-identification problem by proposing a salience matching strategy.
412	Pose Estimation with Unknown Focal Length Using Points, Directions and Lines	Yubin Kuang, Kalle Astrom	In this paper, we study the geometry problems of estimating camera pose with unknown focal length using combination of geometric primitives.
413	Action Recognition and Localization by Hierarchical Space-Time Segments	Shugao Ma, Jianming Zhang, Nazli Ikizler-Cinbis, Stan Sclaroff	We propose Hierarchical Space-Time Segments as a new representation for action recognition and localization.
414	A General Dense Image Matching Framework Combining Direct and Feature-Based Costs	Jim Braux-Zin, Romain Dupont, Adrien Bartoli	We here introduce a general framework that robustly combines direct and feature-based matching.
415	Fast Neighborhood Graph Search Using Cartesian Concatenation	Jing Wang, Jingdong Wang, Gang Zeng, Rui Gan, Shipeng Li, Baining Guo	In this paper, we propose a new data structure for approximate nearest neighbor search.
416	Uncertainty-Driven Efficiently-Sampled Sparse Graphical Models for Concurrent Tumor Segmentation and Atlas Registration	Sarah Parisot, William Wells III, Stephane Chemouny, Hugues Duffau, Nikos Paragios	In this paper we introduce a novel approach for combined segmentation/registration of brain tumors that adapts graph and sampling resolution according to the image content.
417	Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection	Tianfu Wu, Song-Chun Zhu	In this paper, we present a framework of learning cost-sensitive decision policy which is a sequence of two-sided thresholds to execute early rejection or early acceptance based on the accumulative scores at each step.
418	Coherent Object Detection with 3D Geometric Context from a Single Image	Jiyan Pan, Takeo Kanade	In this paper, we develop a RANSAC-CRF framework to detect objects that are geometrically coherent in the 3D world.
419	Unsupervised Visual Domain Adaptation Using Subspace Alignment	Basura Fernando, Amaury Habrard, Marc Sebban, Tinne Tuytelaars	In this paper, we introduce a new domain adaptation (DA) algorithm where the source and target domains are represented by subspaces described by eigenvectors.
420	Semi-supervised Learning for Large Scale Image Cosegmentation	Zhengxiang Wang, Rujie Liu	For semi-supervised cosegmentation in large scale, we propose an effective method by minimizing an energy function, which consists of the inter-image distance, the intraimage distance and the balance term.
421	Mining Multiple Queries for Image Retrieval: On-the-Fly Learning of an Object-Specific Mid-level Representation	Basura Fernando, Tinne Tuytelaars	In this paper we present a new method for object retrieval starting from multiple query images.
422	Event Detection in Complex Scenes Using Interval Temporal Constraints	Yifan Zhang, Qiang Ji, Hanqing Lu	The duration of the event and the unsynchronized time lags between two correlated event intervals are captured by a duration model, so that we can better determine the temporal boundary of the event.
423	Orderless Tracking through Model-Averaged Posterior Estimation	Seunghoon Hong, Suha Kwak, Bohyung Han	We propose a novel offline tracking algorithm based on model-averaged posterior estimation through patch matching across frames.
424	Log-Euclidean Kernels for Sparse Representation and Dictionary Learning	Peihua Li, Qilong Wang, Wangmeng Zuo, Lei Zhang	This paper attempts to tackle this problem by proposing a kernel based method for SR and dictionary learning (DL) of SPD matrices.
425	A Rotational Stereo Model Based on XSlit Imaging	Jinwei Ye, Yu Ji, Jingyi Yu	In this paper, we investigate a different, rotational stereo model on a special multi-perspective camera, the XSlit camera [9, 24].
426	Total Variation Regularization for Functions with Values in a Manifold	Jan Lellmann, Evgeny Strekalovskiy, Sabrina Koetter, Daniel Cremers	In this paper, we propose the first algorithm to solve such problems which applies to arbitrary Riemannian manifolds.
427	Capturing Global Semantic Relationships for Facial Action Unit Recognition	Ziheng Wang, Yongqiang Li, Shangfei Wang, Qiang Ji	In this paper we tackle the problem of facial action unit (AU) recognition by exploiting the complex semantic relationships among AUs, which carry crucial top-down information yet have not been thoroughly exploited.
428	POP: Person Re-identification Post-rank Optimisation	Chunxiao Liu, Chen Change Loy, Shaogang Gong, Guijin Wang	In this study, we present a novel one-shot Post-rank OPtimisation (POP) method, which allows a user to quickly refine their search by either “one-shot” or a couple of sparse negative selections during a re-identification process.
429	Joint Deep Learning for Pedestrian Detection	Wanli Ouyang, Xiaogang Wang	This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation.
430	Visual Semantic Complex Network for Web Images	Shi Qiu, Xiaogang Wang, Xiaoou Tang	This paper proposes modeling the complex web image collections with an automatically generated graph structure called visual semantic complex network (VSCN).
431	Multi-scale Topological Features for Hand Posture Representation and Analysis	Kaoning Hu, Lijun Yin	In this paper, we propose a multi-scale topological feature representation for automatic analysis of hand posture.
432	An Enhanced Structure-from-Motion Paradigm Based on the Absolute Dual Quadric and Images of Circular Points	Lilian Calvet, Pierre Gurdjos	This work aims at introducing a new unified Structurefrom-Motion (SfM) paradigm in which images of circular point-pairs can be combined with images of natural points.
433	Understanding High-Level Semantics by Modeling Traffic Patterns	Hongyi Zhang, Andreas Geiger, Raquel Urtasun	In this paper, we are interested in understanding the semantics of outdoor scenes in the context of autonomous driving.
434	PhotoOCR: Reading Text in Uncontrolled Conditions	Alessandro Bissacco, Mark Cummins, Yuval Netzer, Hartmut Neven	We describe PhotoOCR, a system for text extraction from images.
435	Support Surface Prediction in Indoor Scenes	Ruiqi Guo, Derek Hoiem	In this paper, we present an approach to predict the extent and height of supporting surfaces such as tables, chairs, and cabinet tops from a single RGBD image.
436	Alternating Regression Forests for Object Detection and Pose Estimation	Samuel Schulter, Christian Leistner, Paul Wohlhart, Peter M. Roth, Horst Bischof	We present Alternating Regression Forests (ARFs), a novel regression algorithm that learns a Random Forest by optimizing a global loss function over all trees.
437	Multi-attributed Dictionary Learning for Sparse Coding	Chen-Kuo Chiang, Te-Feng Su, Chih Yen, Shang-Hong Lai	We present a multi-attributed dictionary learning algorithm for sparse coding.
438	Similarity Metric Learning for Face Recognition	Qiong Cao, Yiming Ying, Peng Li	In this paper, we develop a novel regularization framework to learn similarity metrics for unconstrained face verification.
439	Efficient Image Dehazing with Boundary Constraint and Contextual Regularization	Gaofeng Meng, Ying Wang, Jiangyong Duan, Shiming Xiang, Chunhong Pan	In this paper, we propose an efficient regularization method to remove hazes from a single input image.
440	Robust Face Landmark Estimation under Occlusion	Xavier P. Burgos-Artizzu, Pietro Perona, Piotr Dollar	We propose a novel method, called Robust Cascaded Pose Regression (RCPR) which reduces exposure to outliers by detecting occlusions explicitly and using robust shape-indexed features.
441	Finding Actors and Actions in Movies	P. Bojanowski, F. Bach, I. Laptev, J. Ponce, C. Schmid, J. Sivic	We address the problem of learning a joint model of actors and actions in movies using weak supervision provided by scripts.
442	Deblurring by Example Using Dense Correspondence	Yoav Hacohen, Eli Shechtman, Dani Lischinski	This paper presents a new method for deblurring photos using a sharp reference example that contains some shared content with the blurry photo.
443	High Quality Shape from a Single RGB-D Image under Uncalibrated Natural Illumination	Yudeog Han, Joon-Young Lee, In So Kweon	We present a novel framework to estimate detailed shape of diffuse objects with uniform albedo from a single RGB-D image.
444	Discriminative Label Propagation for Multi-object Tracking with Sporadic Appearance Features	K.C. Amit Kumar, Christophe De Vleeschouwer	Given a set of plausible detections, detected at each time instant independently, we investigate how to associate them across time.
445	Attribute Adaptation for Personalized Image Search	Adriana Kovashka, Kristen Grauman	Rather than discount these differences as noise, we propose to learn user-specific attribute models.
446	Regionlets for Generic Object Detection	Xiaoyu Wang, Ming Yang, Shenghuo Zhu, Yuanqing Lin	In view of this, we propose to model an object class by a cascaded boosting classifier which integrates various types of features from competing local regions, named as regionlets.
447	Event Recognition in Photo Collections with a Stopwatch HMM	Lukas Bossard, Matthieu Guillaumin, Luc Van Gool	In this paper, we introduce and release a novel data set of personal photo collections containing more than 61,000 images in 807 collections, annotated with 14 diverse social event classes.
448	Handling Occlusions with Franken-Classifiers	Markus Mathias, Rodrigo Benenson, Radu Timofte, Luc Van Gool	We present a new approach to train such classifiers.
449	Linear Sequence Discriminant Analysis: A Model-Based Dimensionality Reduction Method for Vector Sequences	Bing Su, Xiaoqing Ding	This paper presents a model-based dimensionality reduction method for vector sequences, namely linear sequence discriminant analysis (LSDA) , which attempts to find a subspace in which sequences of the same class are projected together while those of different classes are projected as far as possible.
450	Learning Coupled Feature Spaces for Cross-Modal Matching	Kaiye Wang, Ran He, Wei Wang, Liang Wang, Tieniu Tan	In this paper, we propose a novel coupled linear regression framework to deal with both problems.
451	Structured Light in Sunlight	Mohit Gupta, Qi Yin, Shree K. Nayar	In this paper, we propose the concept of light-concentration to overcome strong ambient illumination.
452	Probabilistic Elastic Part Model for Unsupervised Face Detector Adaptation	Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, Jianchao Yang	We propose an unsupervised detector adaptation algorithm to adapt any offline trained face detector to a specific collection of images, and hence achieve better accuracy.
453	Robust Non-parametric Data Fitting for Correspondence Modeling	Wen-Yan Lin, Ming-Ming Cheng, Shuai Zheng, Jiangbo Lu, Nigel Crook	We propose a generic method for obtaining nonparametric image warps from noisy point correspondences.
454	A Convex Optimization Framework for Active Learning	Ehsan Elhamifar, Guillermo Sapiro, Allen Yang, S. Shankar Sasrty	In this paper, we develop an efficient active learning framework based on convex programming, which can select multiple samples at a time for annotation.
455	Joint Noise Level Estimation from Personal Photo Collections	Yichang Shih, Vivek Kwatra, Troy Chinen, Hui Fang, Sergey Ioffe	We propose a novel technique for jointly estimating noise levels of all face images in a photo collection.