Most Influential CVPR Papers (2024-09)
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) is one of the top computer vision conferences in the world. Paper Digest Team analyzes all papers published on CVPR in the past years, and presents the 15 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2024-09)
To search or review papers within CVPR related to a specific topic, please use the search by venue (CVPR) and review by venue (CVPR) services. To browse the most productive CVPR authors by year ranked by #papers accepted, here are the most productive CVPR authors grouped by year.
This list is created by the Paper Digest Team. Experience the cutting-edge capabilities of Paper Digest, an innovative AI-powered research platform that empowers you to write, review, get answers and more.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Most Influential CVPR Papers (2024-09)
| Year | Rank | Paper | Author(s) |
|---|---|---|---|
| 2024 | 1 | Improved Baselines with Visual Instruction Tuning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present the first systematic study to investigate the design choices of LMMs in a controlled setting under the LLaVA framework. |
Haotian Liu; Chunyuan Li; Yuheng Li; Yong Jae Lee; |
| 2024 | 2 | MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. |
XIANG YUE et. al. |
| 2024 | 3 | 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. |
GUANJUN WU et. al. |
| 2024 | 4 | DETRs Beat YOLOs on Real-time Object Detection IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Nevertheless the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper we propose the Real-Time DEtection TRansformer (RT-DETR) the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. |
YIAN ZHAO et. al. |
| 2024 | 5 | Depth Anything: Unleashing The Power of Large-Scale Unlabeled Data IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work presents Depth Anything a highly practical solution for robust monocular depth estimation. |
LIHE YANG et. al. |
| 2024 | 6 | Wonder3D: Single Image to 3D Using Cross-Domain Diffusion IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we introduce Wonder3D a novel method for generating high-fidelity textured meshes from single-view images with remarkable efficiency. |
XIAOXIAO LONG et. al. |
| 2024 | 7 | LISA: Reasoning Segmentation Via Large Language Model IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we propose a new segmentation task — reasoning segmentation. |
XIN LAI et. al. |
| 2024 | 8 | Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Furthermore implicit methods have difficulty achieving real-time rendering in general dynamic scenes limiting their use in a variety of tasks. To address the issues we propose a deformable 3D Gaussians splatting method that reconstructs scenes using 3D Gaussians and learns them in canonical space with a deformation field to model monocular dynamic scenes. |
ZIYI YANG et. al. |
| 2024 | 9 | InstantBooth: Personalized Text-to-Image Generation Without Test-Time Finetuning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However these methods often necessitate extensive test-time finetuning for each new concept leading to inefficiencies in both time and scalability. To address this challenge we introduce InstantBooth an innovative approach leveraging existing text-to-image models for instantaneous text-guided image personalization eliminating the need for test-time finetuning. |
Jing Shi; Wei Xiong; Zhe Lin; Hyun Joon Jung; |
| 2024 | 10 | MPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we introduce a versatile multi-modal large language model mPLUG-Owl2 which effectively leverages modality collaboration to improve performance in both text and multi-modal tasks. |
QINGHAO YE et. al. |
| 2024 | 11 | CogAgent: A Visual Language Model for GUI Agents IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce CogAgent an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. |
WENYI HONG et. al. |
| 2024 | 12 | InternVL: Scaling Up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we design a large-scale vision-language foundation model (InternVL) which scales up the vision foundation model to 6 billion parameters and progressively aligns it with the LLM using web-scale image-text data from various sources. |
ZHE CHEN et. al. |
| 2024 | 13 | AnyDoor: Zero-shot Object-level Image Customization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work presents AnyDoor a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations with desired shapes. |
XI CHEN et. al. |
| 2024 | 14 | Text-to-3D Using Gaussian Splatting IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response this paper proposes GSGEN a novel method that adopts Gaussian Splatting a recent state-of-the-art representation to text-to-3D generation. |
Zilong Chen; Feng Wang; Yikai Wang; Huaping Liu; |
| 2024 | 15 | Video-P2P: Video Editing with Cross-attention Control IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For attention control we introduce a novel decoupled-guidance strategy which uses different guidance strategies for the source and target prompts. |
Shaoteng Liu; Yuechen Zhang; Wenbo Li; Zhe Lin; Jiaya Jia; |
| 2023 | 1 | YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the topics, we propose a trainable bag-of-freebies oriented solution. |
Chien-Yao Wang; Alexey Bochkovskiy; Hong-Yuan Mark Liao; |
| 2023 | 2 | DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a new approach for "personalization" of text-to-image diffusion models. |
NATANIEL RUIZ et. al. |
| 2023 | 3 | InstructPix2Pix: Learning To Follow Image Editing Instructions IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. |
Tim Brooks; Aleksander Holynski; Alexei A. Efros; |
| 2023 | 4 | Magic3D: High-Resolution Text-to-3D Content Creation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the method has two inherent limitations: 1) optimization of the NeRF representation is extremely slow, 2) NeRF is supervised by images at a low resolution (64×64), thus leading to low-quality 3D models with a long wait time. In this paper, we address these limitations by utilizing a two-stage coarse-to-fine optimization framework. |
CHEN-HSUAN LIN et. al. |
| 2023 | 5 | Imagic: Text-Based Real Image Editing With Diffusion Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-based semantic edits to a single real image. |
BAHJAT KAWAR et. al. |
| 2023 | 6 | Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. |
ANDREAS BLATTMANN et. al. |
| 2023 | 7 | ImageBind: One Embedding Space To Bind Them All IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present ImageBind, an approach to learn a joint embedding across six different modalities – images, text, audio, depth, thermal, and IMU data. |
ROHIT GIRDHAR et. al. |
| 2023 | 8 | Multi-Concept Customization of Text-to-Image Diffusion IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose Custom Diffusion, an efficient method for augmenting existing text-to-image models. |
Nupur Kumari; Bingliang Zhang; Richard Zhang; Eli Shechtman; Jun-Yan Zhu; |
| 2023 | 9 | NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce an accurate inversion technique and thus facilitate an intuitive text-based modification of the image. |
Ron Mokady; Amir Hertz; Kfir Aberman; Yael Pritch; Daniel Cohen-Or; |
| 2023 | 10 | Objaverse: A Universe of Annotated 3D Objects IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite considerable interest and potential applications in 3D vision, datasets of high-fidelity 3D models continue to be mid-sized with limited diversity of object categories. Addressing this gap, we present Objaverse 1.0, a large dataset of objects with 800K+ (and growing) 3D models with descriptive captions, tags, and animations. |
MATT DEITKE et. al. |
| 2023 | 11 | EVA: Exploring The Limits of Masked Visual Representation Learning at Scale IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. |
YUXIN FANG et. al. |
| 2023 | 12 | Reproducible Scaling Laws for Contrastive Language-Image Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, previous work on scaling laws has primarily used private data & models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. |
MEHDI CHERTI et. al. |
| 2023 | 13 | InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. |
WENHAI WANG et. al. |
| 2023 | 14 | ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop an efficient and fully-convolutional masked autoencoder framework. |
SANGHYUN WOO et. al. |
| 2023 | 15 | Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field. |
Haochen Wang; Xiaodan Du; Jiahao Li; Raymond A. Yeh; Greg Shakhnarovich; |
| 2022 | 1 | High-Resolution Image Synthesis With Latent Diffusion Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. |
Robin Rombach; Andreas Blattmann; Dominik Lorenz; Patrick Esser; Björn Ommer; |
| 2022 | 2 | Masked Autoencoders Are Scalable Vision Learners IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. |
KAIMING HE et. al. |
| 2022 | 3 | A ConvNet for The 2020s IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we reexamine the design spaces and test the limits of what a pure ConvNet can achieve. |
ZHUANG LIU et. al. |
| 2022 | 4 | Masked-Attention Mask Transformer for Universal Image Segmentation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). |
Bowen Cheng; Ishan Misra; Alexander G. Schwing; Alexander Kirillov; Rohit Girdhar; |
| 2022 | 5 | Restormer: Efficient Transformer for High-Resolution Image Restoration IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images. |
SYED WAQAS ZAMIR et. al. |
| 2022 | 6 | Swin Transformer V2: Scaling Up Capacity and Resolution IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present techniques for scaling Swin Transformer [??] up to 3 billion parameters and making it capable of training with images of up to 1,536×1,536 resolution. |
ZE LIU et. al. |
| 2022 | 7 | Plenoxels: Radiance Fields Without Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. |
SARA FRIDOVICH-KEIL et. al. |
| 2022 | 8 | Video Swin Transformer IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. |
ZE LIU et. al. |
| 2022 | 9 | Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an extension of mip-NeRF (a NeRF variant that addresses sampling and aliasing) that uses a non-linear scene parameterization, online distillation, and a novel distortion-based regularizer to overcome the challenges presented by unbounded scenes. |
Jonathan T. Barron; Ben Mildenhall; Dor Verbin; Pratul P. Srinivasan; Peter Hedman; |
| 2022 | 10 | SimMIM: A Simple Framework for Masked Image Modeling IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents SimMIM, a simple framework for masked image modeling. |
ZHENDA XIE et. al. |
| 2022 | 11 | Uformer: A General U-Shaped Transformer for Image Restoration IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. |
ZHENDONG WANG et. al. |
| 2022 | 12 | RePaint: Inpainting Using Denoising Diffusion Probabilistic Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks. |
ANDREAS LUGMAYR et. al. |
| 2022 | 13 | Efficient Geometry-Aware 3D Generative Adversarial Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generated images and the latter adversely affects multi-view consistency and shape quality. In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. |
ERIC R. CHAN et. al. |
| 2022 | 14 | Conditional Prompt Learning for Vision-Language Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the problem, we propose Conditional Context Optimization (CoCoOp), which extends CoOp by further learning a lightweight neural network to generate for each image an input-conditional token (vector). |
Kaiyang Zhou; Jingkang Yang; Chen Change Loy; Ziwei Liu; |
| 2022 | 15 | Scaling Vision Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While the laws for scaling Transformer language models have been studied, it is unknown how Vision Transformers scale. To address this, we scale ViT models and data, both up and down, and characterize the relationships between error rate, data, and compute. |
Xiaohua Zhai; Alexander Kolesnikov; Neil Houlsby; Lucas Beyer; |
| 2021 | 1 | Exploring Simple Siamese Representation Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. |
Xinlei Chen; Kaiming He; |
| 2021 | 2 | Rethinking Semantic Segmentation From A Sequence-to-Sequence Perspective With Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. |
SIXIAO ZHENG et. al. |
| 2021 | 3 | Coordinate Attention for Efficient Mobile Network Design IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel attention mechanism for mobile networks by embedding positional information into channel attention, which we call "coordinate attention". |
Qibin Hou; Daquan Zhou; Jiashi Feng; |
| 2021 | 4 | Taming Transformers for High-Resolution Image Synthesis IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular, we present the first results on semantically-guided synthesis of megapixel images with transformers. |
Patrick Esser; Robin Rombach; Bjorn Ommer; |
| 2021 | 5 | PixelNeRF: Neural Radiance Fields From One or Few Images IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. |
Alex Yu; Vickie Ye; Matthew Tancik; Angjoo Kanazawa; |
| 2021 | 6 | Pre-Trained Image Processing Transformer IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the low-level computer vision task (e.g., denoising, super-resolution and deraining) and develop a new pre-trained model, namely, image processing transformer (IPT). |
HANTING CHEN et. al. |
| 2021 | 7 | Center-Based 3D Object Detection and Tracking IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we instead propose to represent, detect, and track 3D objects as points. |
Tianwei Yin; Xingyi Zhou; Philipp Krahenbuhl; |
| 2021 | 8 | NeRF in The Wild: Neural Radiance Fields for Unconstrained Photo Collections IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a learning-based method for synthesizingnovel views of complex scenes using only unstructured collections of in-the-wild photographs. |
RICARDO MARTIN-BRUALLA et. al. |
| 2021 | 9 | Multi-Stage Progressive Image Restoration IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel synergistic design that can optimally balance these competing goals. |
SYED WAQAS ZAMIR et. al. |
| 2021 | 10 | RepVGG: Making VGG-Style ConvNets Great Again IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3×3 convolution and ReLU, while the training-time model has a multi-branch topology. |
XIAOHAN DING et. al. |
| 2021 | 11 | Natural Adversarial Examples IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade. |
Dan Hendrycks; Kevin Zhao; Steven Basart; Jacob Steinhardt; Dawn Song; |
| 2021 | 12 | D-NeRF: Neural Radiance Fields for Dynamic Scenes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce D-NeRF, a method that extends neural radiance fields to a dynamic domain, allowing to reconstruct and render novel images of objects under rigid and non-rigid motions. |
Albert Pumarola; Enric Corona; Gerard Pons-Moll; Francesc Moreno-Noguer; |
| 2021 | 13 | Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a generic image-to-image translation framework, pixel2style2pixel (pSp). |
ELAD RICHARDSON et. al. |
| 2021 | 14 | Scaled-YOLOv4: Scaling Cross Stage Partial Network IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a network scaling approach that modifies not only the depth, width, resolution, but also structure of the network. |
Chien-Yao Wang; Alexey Bochkovskiy; Hong-Yuan Mark Liao; |
| 2021 | 15 | Sparse R-CNN: End-to-End Object Detection With Learnable Proposals IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Sparse R-CNN, a purely sparse method for object detection in images. |
PEIZE SUN et. al. |
| 2020 | 1 | Momentum Contrast for Unsupervised Visual Representation Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Momentum Contrast (MoCo) for unsupervised visual representation learning. |
Kaiming He; Haoqi Fan; Yuxin Wu; Saining Xie; Ross Girshick; |
| 2020 | 2 | Analyzing and Improving The Image Quality of StyleGAN IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. |
TERO KARRAS et. al. |
| 2020 | 3 | NuScenes: A Multimodal Dataset for Autonomous Driving IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. |
HOLGER CAESAR et. al. |
| 2020 | 4 | EfficientDet: Scalable and Efficient Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. |
Mingxing Tan; Ruoming Pang; Quoc V. Le; |
| 2020 | 5 | ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To overcome the paradox of performance and complexity trade-off, this paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain. |
QILONG WANG et. al. |
| 2020 | 6 | Scalability in Perception for Autonomous Driving: Waymo Open Dataset IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In an effort to help align the research community’s contributions with real-world self-driving problems, we introduce a new large scale, high quality, diverse dataset. |
PEI SUN et. al. |
| 2020 | 7 | Self-Training With Noisy Student Improves ImageNet Classification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. |
Qizhe Xie; Minh-Thang Luong; Eduard Hovy; Quoc V. Le; |
| 2020 | 8 | GhostNet: More Features From Cheap Operations IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a novel Ghost module to generate more feature maps from cheap operations. |
KAI HAN et. al. |
| 2020 | 9 | BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. |
FISHER YU et. al. |
| 2020 | 10 | SuperGlue: Learning Feature Matching With Graph Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. |
Paul-Edouard Sarlin; Daniel DeTone; Tomasz Malisiewicz; Andrew Rabinovich; |
| 2020 | 11 | StarGAN V2: Diverse Image Synthesis for Multiple Domains IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose StarGAN v2, a single framework that tackles both and shows significantly improved results over the baselines. |
Yunjey Choi; Youngjung Uh; Jaejun Yoo; Jung-Woo Ha; |
| 2020 | 12 | PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. |
SHAOSHUAI SHI et. al. |
| 2020 | 13 | Designing Network Design Spaces IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a new network design paradigm. |
Ilija Radosavovic; Raj Prateek Kosaraju; Ross Girshick; Kaiming He; Piotr Dollar; |
| 2020 | 14 | Self-Supervised Learning of Pretext-Invariant Representations IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we develop Pretext-Invariant Representation Learning (PIRL, pronounced as `pearl’) that learns invariant representations based on pretext tasks. |
Ishan Misra; Laurens van der Maaten; |
| 2020 | 15 | Bridging The Gap Between Anchor-Based and Anchor-Free Detection Via Adaptive Training Sample Selection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. |
Shifeng Zhang; Cheng Chi; Yongqiang Yao; Zhen Lei; Stan Z. Li; |
| 2019 | 1 | A Style-Based Generator Architecture for Generative Adversarial Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. Finally, we introduce a new, highly varied and high-quality dataset of human faces. |
Tero Karras; Samuli Laine; Timo Aila; |
| 2019 | 2 | ArcFace: Additive Angular Margin Loss for Deep Face Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. |
Jiankang Deng; Jia Guo; Niannan Xue; Stefanos Zafeiriou; |
| 2019 | 3 | Dual Attention Network for Scene Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the self-attention mechanism. |
JUN FU et. al. |
| 2019 | 4 | Deep High-Resolution Representation Learning for Human Pose Estimation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. |
Ke Sun; Bin Xiao; Dong Liu; Jingdong Wang; |
| 2019 | 5 | Generalized Intersection Over Union: A Metric and A Loss for Bounding Box Regression IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the this weakness by introducing a generalized version of IoU as both a new loss and a new metric. |
HAMID REZATOFIGHI et. al. |
| 2019 | 6 | DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data. |
Jeong Joon Park; Peter Florence; Julian Straub; Richard Newcombe; Steven Lovegrove; |
| 2019 | 7 | PointPillars: Fast Encoders for Object Detection From Point Clouds IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. |
ALEX H. LANG et. al. |
| 2019 | 8 | MnasNet: Platform-Aware Neural Architecture Search for Mobile IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. |
MINGXING TAN et. al. |
| 2019 | 9 | Occupancy Networks: Learning 3D Reconstruction in Function Space IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. |
Lars Mescheder; Michael Oechsle; Michael Niemeyer; Sebastian Nowozin; Andreas Geiger; |
| 2019 | 10 | Semantic Image Synthesis With Spatially-Adaptive Normalization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. |
Taesung Park; Ming-Yu Liu; Ting-Chun Wang; Jun-Yan Zhu; |
| 2019 | 11 | PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose PointRCNN for 3D object detection from raw point cloud. |
Shaoshuai Shi; Xiaogang Wang; Hongsheng Li; |
| 2019 | 12 | AutoAugment: Learning Augmentation Strategies From Data IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. |
Ekin D. Cubuk; Barret Zoph; Dandelion Mane; Vijay Vasudevan; Quoc V. Le; |
| 2019 | 13 | Class-Balanced Loss Based on Effective Number of Samples IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. |
Yin Cui; Menglin Jia; Tsung-Yi Lin; Yang Song; Serge Belongie; |
| 2019 | 14 | Selective Kernel Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. |
Xiang Li; Wenhai Wang; Xiaolin Hu; Jian Yang; |
| 2019 | 15 | Deformable ConvNets V2: More Deformable, Better Results IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. |
Xizhou Zhu; Han Hu; Stephen Lin; Jifeng Dai; |
| 2018 | 1 | Squeeze-and-Excitation Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we focus on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. |
Jie Hu; Li Shen; Gang Sun; |
| 2018 | 2 | MobileNetV2: Inverted Residuals and Linear Bottlenecks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe a new mobile architecture, mbox{MobileNetV2}, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. |
Mark Sandler; Andrew Howard; Menglong Zhu; Andrey Zhmoginov; Liang-Chieh Chen; |
| 2018 | 3 | The Unreasonable Effectiveness of Deep Features As A Perceptual Metric IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To answer these questions, we introduce a new dataset of human perceptual similarity judgments. |
Richard Zhang; Phillip Isola; Alexei A. Efros; Eli Shechtman; Oliver Wang; |
| 2018 | 4 | Non-Local Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies. |
Xiaolong Wang; Ross Girshick; Abhinav Gupta; Kaiming He; |
| 2018 | 5 | ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). |
Xiangyu Zhang; Xinyu Zhou; Mengxiao Lin; Jian Sun; |
| 2018 | 6 | Learning Transferable Architectures for Scalable Image Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study a method to learn the model architectures directly on the dataset of interest. |
Barret Zoph; Vijay Vasudevan; Jonathon Shlens; Quoc V. Le; |
| 2018 | 7 | Path Aggregation Network for Instance Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framework. |
Shu Liu; Lu Qi; Haifang Qin; Jianping Shi; Jiaya Jia; |
| 2018 | 8 | Cascade R-CNN: Delving Into High Quality Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, … |
Zhaowei Cai; Nuno Vasconcelos; |
| 2018 | 9 | Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. |
PETER ANDERSON et. al. |
| 2018 | 10 | Learning to Compare: Relation Network for Few-Shot Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. |
FLOOD SUNG et. al. |
| 2018 | 11 | High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). |
TING-CHUN WANG et. al. |
| 2018 | 12 | StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. |
YUNJEY CHOI et. al. |
| 2018 | 13 | VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network. |
Yin Zhou; Oncel Tuzel; |
| 2018 | 14 | Unsupervised Feature Learning Via Non-Parametric Instance Discrimination IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We formulate this intuition as a non-parametric classification problem at the instance-level, and use noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes. |
Zhirong Wu; Yuanjun Xiong; Stella X. Yu; Dahua Lin; |
| 2018 | 15 | Residual Dense Network for Image Super-Resolution IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose dense feature fusion (DFF) for image super-resolution (SR). |
Yulun Zhang; Yapeng Tian; Yu Kong; Bineng Zhong; Yun Fu; |
| 2017 | 1 | Densely Connected Convolutional Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. |
Gao Huang; Zhuang Liu; Laurens van der Maaten; Kilian Q. Weinberger; |
| 2017 | 2 | Feature Pyramid Networks For Object Detection IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. |
TSUNG-YI LIN et. al. |
| 2017 | 3 | Image-To-Image Translation With Conditional Adversarial Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. |
Phillip Isola; Jun-Yan Zhu; Tinghui Zhou; Alexei A. Efros; |
| 2017 | 4 | YOLO9000: Better, Faster, Stronger IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. |
Joseph Redmon; Ali Farhadi; |
| 2017 | 5 | Xception: Deep Learning With Depthwise Separable Convolutions IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). |
Francois Chollet; |
| 2017 | 6 | PointNet: Deep Learning On Point Sets For 3D Classification And Segmentation IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. |
Charles R. Qi; Hao Su; Kaichun Mo; Leonidas J. Guibas; |
| 2017 | 7 | Pyramid Scene Parsing Network IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). |
Hengshuang Zhao; Jianping Shi; Xiaojuan Qi; Xiaogang Wang; Jiaya Jia; |
| 2017 | 8 | Photo-Realistic Single Image Super-Resolution Using A Generative Adversarial Network IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). |
CHRISTIAN LEDIG et. al. |
| 2017 | 9 | Aggregated Residual Transformations For Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a simple, highly modularized network architecture for image classification. |
Saining Xie; Ross Girshick; Piotr Dollar; Zhuowen Tu; Kaiming He; |
| 2017 | 10 | Quo Vadis, Action Recognition? A New Model And The Kinetics Dataset IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics. |
Joao Carreira; Andrew Zisserman; |
| 2017 | 11 | Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach to efficiently detect the 2D pose of multiple people in an image. |
Zhe Cao; Tomas Simon; Shih-En Wei; Yaser Sheikh; |
| 2017 | 12 | Adversarial Discriminative Domain Adaptation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. |
Eric Tzeng; Judy Hoffman; Kate Saenko; Trevor Darrell; |
| 2017 | 13 | ScanNet: Richly-Annotated 3D Reconstructions Of Indoor Scenes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. |
ANGELA DAI et. al. |
| 2017 | 14 | ICaRL: Incremental Classifier And Representation Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. |
Sylvestre-Alvise Rebuffi; Alexander Kolesnikov; Georg Sperl; Christoph H. Lampert; |
| 2017 | 15 | Residual Attention Network For Image Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose Residual Attention Network, a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. |
FEI WANG et. al. |
| 2016 | 1 | Deep Residual Learning For Image Recognition IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. |
Kaiming He; Xiangyu Zhang; Shaoqing Ren; Jian Sun; |
| 2016 | 2 | You Only Look Once: Unified, Real-Time Object Detection IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present YOLO, a new approach to object detection. |
Joseph Redmon; Santosh Divvala; Ross Girshick; Ali Farhadi; |
| 2016 | 3 | Rethinking The Inception Architecture For Computer Vision IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we are exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible. |
Christian Szegedy; Vincent Vanhoucke; Sergey Ioffe; Jon Shlens; Zbigniew Wojna; |
| 2016 | 4 | The Cityscapes Dataset For Semantic Urban Scene Understanding IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. |
MARIUS CORDTS et. al. |
| 2016 | 5 | Learning Deep Features For Discriminative Localization IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on image-level labels. |
Bolei Zhou; Aditya Khosla; Agata Lapedriza; Aude Oliva; Antonio Torralba; |
| 2016 | 6 | Accurate Image Super-Resolution Using Very Deep Convolutional Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a highly accurate single image superresolution (SR) method. |
Jiwon Kim; Jung Kwon Lee; Kyoung Mu Lee; |
| 2016 | 7 | Context Encoders: Feature Learning By Inpainting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. |
Deepak Pathak; Philipp Krahenbuhl; Jeff Donahue; Trevor Darrell; Alexei A. Efros; |
| 2016 | 8 | Image Style Transfer Using Convolutional Neural Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce A Neural Algorithm of Artistic Style that can separate and recombine the image content and style of natural images. |
Leon A. Gatys; Alexander S. Ecker; Matthias Bethge; |
| 2016 | 9 | Real-Time Single Image And Video Super-Resolution Using An Efficient Sub-Pixel Convolutional Neural Network IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. |
WENZHE SHI et. al. |
| 2016 | 10 | DeepFool: A Simple And Accurate Method To Fool Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we fill this gap and propose the DeepFool algorithm to efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these classifiers. |
Seyed-Mohsen Moosavi-Dezfooli; Alhussein Fawzi; Pascal Frossard; |
| 2016 | 11 | Structure-From-Motion Revisited IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new SfM technique that improves upon the state of the art to make a further step towards this ultimate goal. |
Johannes L. Schonberger; Jan-Michael Frahm; |
| 2016 | 12 | Convolutional Pose Machines IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. |
Shih-En Wei; Varun Ramakrishna; Takeo Kanade; Yaser Sheikh; |
| 2016 | 13 | Social LSTM: Human Trajectory Prediction In Crowded Spaces IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our work, we propose a data-driven approach to learn these human-human interactions for predicting their future trajectories. |
ALEXANDRE ALAHI et. al. |
| 2016 | 14 | Convolutional Two-Stream Network Fusion For Video Action Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. |
Christoph Feichtenhofer; Axel Pinz; Andrew Zisserman; |
| 2016 | 15 | A Large Dataset To Train Convolutional Networks For Disparity, Optical Flow, And Scene Flow Estimation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. |
NIKOLAUS MAYER et. al. |
| 2015 | 1 | Going Deeper With Convolutions IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC2014). |
CHRISTIAN SZEGEDY et. al. |
| 2015 | 2 | Fully Convolutional Networks For Semantic Segmentation IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our key insight is to build fully convolutional networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. |
Jonathan Long; Evan Shelhamer; Trevor Darrell; |
| 2015 | 3 | FaceNet: A Unified Embedding For Face Recognition And Clustering IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. |
Florian Schroff; Dmitry Kalenichenko; James Philbin; |
| 2015 | 4 | Long-Term Recurrent Convolutional Networks For Visual Recognition And Description IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image to sentence generation problems, and video narration challenges. |
JEFFREY DONAHUE et. al. |
| 2015 | 5 | Show And Tell: A Neural Image Caption Generator IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. |
Oriol Vinyals; Alexander Toshev; Samy Bengio; Dumitru Erhan; |
| 2015 | 6 | Deep Visual-Semantic Alignments For Generating Image Descriptions IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a model that generates natural language descriptions of images and their regions. |
Andrej Karpathy; Li Fei-Fei; |
| 2015 | 7 | 3D ShapeNets: A Deep Representation For Volumetric Shapes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. |
ZHIRONG WU et. al. |
| 2015 | 8 | CIDEr: Consensus-Based Image Description Evaluation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel paradigm for evaluating image descriptions that uses human consensus. |
Ramakrishna Vedantam; C. Lawrence Zitnick; Devi Parikh; |
| 2015 | 9 | Deep Neural Networks Are Easily Fooled: High Confidence Predictions For Unrecognizable Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A recent study revealed that changing an image (e.g. of a lion) in a way imperceptible to humans can cause a DNN to label the image as something else entirely (e.g. mislabeling a lion a library). |
Anh Nguyen; Jason Yosinski; Jeff Clune; |
| 2015 | 10 | Single Image Super-Resolution From Transformed Self-Exemplars IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we extend self-similarity based SR to overcome this drawback. |
Jia-Bin Huang; Abhishek Singh; Narendra Ahuja; |
| 2015 | 11 | Beyond Short Snippets: Deep Networks For Video Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose two methods capable of han- dling full length videos. |
JOE YUE-HEI NG et. al. |
| 2015 | 12 | ActivityNet: A Large-Scale Video Benchmark For Human Activity Understanding IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce ActivityNet: a new large-scale video benchmark for human activity understanding. |
Fabian Caba Heilbron; Victor Escorcia; Bernard Ghanem; Juan Carlos Niebles; |
| 2015 | 13 | Person Re-Identification By Local Maximal Occurrence Representation And Metric Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA). |
Shengcai Liao; Yang Hu; Xiangyu Zhu; Stan Z. Li; |
| 2015 | 14 | Object Scene Flow For Autonomous Vehicles IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. We obtain this dataset by annotating 400 dynamic scenes from the KITTI raw data collection using detailed 3D CAD models for all vehicles in motion. |
Moritz Menze; Andreas Geiger; |
| 2015 | 15 | Understanding Deep Image Representations By Inverting Them IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we conduct a direct analysis of the visual information contained in representations by asking the following question: given an encoding of an image, to which extent is it possible to reconstruct the image itself? |
Aravindh Mahendran; Andrea Vedaldi; |
| 2014 | 1 | Rich Feature Hierarchies For Accurate Object Detection And Semantic Segmentation IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012—achieving a mAP of 53.3%. |
Ross Girshick; Jeff Donahue; Trevor Darrell; Jitendra Malik; |
| 2014 | 2 | Large-scale Video Classification With Convolutional Neural Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We study multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggest a multiresolution, foveated architecture as a promising way of speeding up the training. |
ANDREJ KARPATHY et. al. |
| 2014 | 3 | DeepFace: Closing The Gap To Human-Level Performance In Face Verification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. |
Yaniv Taigman; Ming Yang; Marc’Aurelio Ranzato; Lior Wolf; |
| 2014 | 4 | Learning And Transferring Mid-Level Image Representations Using Convolutional Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we show how image representations learned with CNNs on large-scale annotated datasets can be efficiently transferred to other visual recognition tasks with limited amount of training data. |
Maxime Oquab; Leon Bottou; Ivan Laptev; Josef Sivic; |
| 2014 | 5 | DeepPose: Human Pose Estimation Via Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method for human pose estimation based on Deep Neural Networks (DNNs). |
Alexander Toshev; Christian Szegedy; |
| 2014 | 6 | One Millisecond Face Alignment With An Ensemble Of Regression Trees IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a general framework based on gradient boosting for learning an ensemble of regression trees that optimizes the sum of square error loss and naturally handles missing or partially labelled data. |
Vahid Kazemi; Josephine Sullivan; |
| 2014 | 7 | 2D Human Pose Estimation: New Benchmark And State Of The Art Analysis IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce a novel benchmark MPII Human Pose that makes a significant advance in terms of diversity and difficulty, a contribution that we feel is required for future developments in human body models. We provide a rich set of labels including positions of body joints, full 3D torso and head orientation, occlusion labels for joints and body parts, and activity labels. |
Mykhaylo Andriluka; Leonid Pishchulin; Peter Gehler; Bernt Schiele; |
| 2014 | 8 | DeepReID: Deep Filter Pairing Neural Network For Person Re-Identification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter. We build the largest benchmark re-id dataset with 13,164 images of 1,360 pedestrians. |
Wei Li; Rui Zhao; Tong Xiao; Xiaogang Wang; |
| 2014 | 9 | Describing Textures In The Wild IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Aiming at supporting this dimension in image understanding, we address the problem of describing textures with semantic attributes. |
Mircea Cimpoi; Subhransu Maji; Iasonas Kokkinos; Sammy Mohamed; Andrea Vedaldi; |
| 2014 | 10 | Deep Learning Face Representation From Predicting 10,000 Classes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes to learn a set of high-level feature representations through deep learning, referred to as Deep hidden IDentity features (DeepID), for face verification. |
Yi Sun; Xiaogang Wang; Xiaoou Tang; |
| 2014 | 11 | Weighted Nuclear Norm Minimization With Application To Image Denoising IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we study the weighted nuclear norm minimization (WNNM) problem, where the singular values are assigned different weights. |
Shuhang Gu; Lei Zhang; Wangmeng Zuo; Xiangchu Feng; |
| 2014 | 12 | Adaptive Color Attributes For Real-Time Visual Tracking IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper investigates the contribution of color in a tracking-by-detection framework. |
Martin Danelljan; Fahad Shahbaz Khan; Michael Felsberg; Joost van de Weijer; |
| 2014 | 13 | Learning Fine-grained Image Similarity With Deep Ranking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. |
JIANG WANG et. al. |
| 2014 | 14 | Human Action Recognition By Representing 3D Skeletons As Points In A Lie Group IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new skeletal representation that explicitly models the 3D geometric relationships between various body parts using rotations and translations in 3D space. |
Raviteja Vemulapalli; Felipe Arrate; Rama Chellappa; |
| 2014 | 15 | The Role Of Context For Object Detection And Semantic Segmentation In The Wild IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. |
ROOZBEH MOTTAGHI et. al. |
| 2013 | 1 | Online Object Tracking: A Benchmark IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field. |
Yi Wu; Jongwoo Lim; Ming-Hsuan Yang; |
| 2013 | 2 | Saliency Detection Via Graph-Based Manifold Ranking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Instead of considering the contrast between the salient objects and their surrounding regions, we consider both foreground and background cues in a different way. We also create a more difficult benchmark database containing 5,172 images to test the proposed saliency model and make this database publicly available with this paper for further studies in the saliency field. |
Chuan Yang; Lihe Zhang; Huchuan Lu; Xiang Ruan; Ming-Hsuan Yang; |
| 2013 | 3 | Supervised Descent Method And Its Applications To Face Alignment IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address these issues, this paper proposes a Supervised Descent Method (SDM) for minimizing a Non-linear Least Squares (NLS) function. |
Xuehan Xiong; Fernando De la Torre; |
| 2013 | 4 | Hierarchical Saliency Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. |
Qiong Yan; Li Xu; Jianping Shi; Jiaya Jia; |
| 2013 | 5 | Deep Convolutional Network Cascade For Facial Point Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new approach for estimation of the positions of facial keypoints with three-level carefully designed convolutional networks. |
Yi Sun; Xiaogang Wang; Xiaoou Tang; |
| 2013 | 6 | Salient Object Detection: A Discriminative Regional Feature Integration Approach IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we regard saliency map computation as a regression problem. |
HUAIZU JIANG et. al. |
| 2013 | 7 | Unsupervised Salience Learning For Person Re-identification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning. |
Rui Zhao; Wanli Ouyang; Xiaogang Wang; |
| 2013 | 8 | Unnatural L0 Sparse Representation For Natural Image Deblurring IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show in this paper that the success of previous maximum a posterior (MAP) based blur removal methods partly stems from their respective intermediate steps, which implicitly or explicitly create an unnatural representation containing salient image structures. |
Li Xu; Shicheng Zheng; Jiaya Jia; |
| 2013 | 9 | HON4D: Histogram Of Oriented 4D Normals For Activity Recognition From Depth Sequences IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new descriptor for activity recognition from videos acquired by a depth sensor. |
Omar Oreifej; Zicheng Liu; |
| 2013 | 10 | SLAM++: Simultaneous Localisation And Mapping At The Level Of Objects IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the major advantages of a new ‘object oriented’ 3D SLAM paradigm, which takes full advantage in the loop of prior knowledge that many scenes consist of repeated, domain-specific objects and structures. |
Renato F. Salas-Moreno; Richard A. Newcombe; Hauke Strasdat; Paul H.J. Kelly; Andrew J. Davison; |
| 2013 | 11 | Multi-source Multi-scale Counting In Extremely Dense Crowd Images IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to leverage multiple sources of information to compute an estimate of the number of individuals present in an extremely dense crowd visible in a single image. |
Haroon Idrees; Imran Saleemi; Cody Seibert; Mubarak Shah; |
| 2013 | 12 | Pedestrian Detection With Unsupervised Multi-stage Feature Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Adding to the list of successful applications of deep learning methods to vision, we report state-of-theart and competitive results on all major pedestrian datasets with a convolutional network model. |
Pierre Sermanet; Koray Kavukcuoglu; Soumith Chintala; Yann Lecun; |
| 2013 | 13 | Scene Coordinate Regression Forests For Camera Relocalization In RGB-D Images IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image. |
JAMIE SHOTTON et. al. |
| 2013 | 14 | All About VLAD IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The objective of this paper is large scale object instance retrieval, given a query image. |
Relja Arandjelovic; Andrew Zisserman; |
| 2013 | 15 | Perceptual Organization And Recognition Of Indoor Scenes From RGB-D Images IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose algorithms for object boundary detection and hierarchical segmentation that generalize the gP b ucm approach of [2] by making effective use of depth information. |
Saurabh Gupta; Pablo Arbelaez; Jitendra Malik; |
| 2012 | 1 | Are We Ready For Autonomous Driving? The KITTI Vision Benchmark Suite IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection. |
A. Geiger; P. Lenz and R. Urtasun; |
| 2012 | 2 | Multi-column Deep Neural Networks For Image Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. Our … |
D. Ciregan; U. Meier and J. Schmidhuber; |
| 2012 | 3 | Face Detection, Pose Estimation, And Landmark Localization In The Wild IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a unified model for face detection, pose estimation, and landmark estimation in real-world, cluttered images. |
X. Zhu and D. Ramanan; |
| 2012 | 4 | Geodesic Flow Kernel For Unsupervised Domain Adaptation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new kernel-based method that takes advantage of such structures. |
B. Gong; Y. Shi; F. Sha and K. Grauman; |
| 2012 | 5 | FREAK: Fast Retina Keypoint IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To best address the current requirements, we propose a novel keypoint descriptor inspired by the human visual system and more precisely the retina, coined Fast Retina Keypoint (FREAK). |
A. Alahi; R. Ortiz and P. Vandergheynst; |
| 2012 | 6 | Saliency Filters: Contrast Based Filtering For Salient Region Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we reconsider some of the design choices of previous methods and propose a conceptually clear and intuitive algorithm for contrast-based saliency estimation. |
F. Perazzi; P. Kr�henb�hl; Y. Pritch and A. Hornung; |
| 2012 | 7 | Cats And Dogs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate the fine grained object categorization problem of determining the breed of animal from an image. To this end we introduce a new annotated dataset of pets covering 37 different breeds of cats and dogs. |
O. M. Parkhi; A. Vedaldi; A. Zisserman and C. V. Jawahar; |
| 2012 | 8 | Large Scale Metric Learning From Equivalence Constraints IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we raise important issues on scalability and the required degree of supervision of existing Mahalanobis metric learning methods. |
M. K�stinger; M. Hirzer; P. Wohlhart; P. M. Roth and H. Bischof; |
| 2012 | 9 | Three Things Everyone Should Know To Improve Object Retrieval IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The objective of this work is object retrieval in large scale image datasets, where the object is specified by an image query and retrieval should be immediate at run time in the manner of Video Google [28]. |
R. Arandjelovic and A. Zisserman; |
| 2012 | 10 | Supervised Hashing With Kernels IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel kernel-based supervised hashing model which requires a limited amount of supervised information, i.e., similar and dissimilar data pairs, and a feasible training cost in achieving high quality hashing. |
W. Liu; J. Wang; R. Ji; Y. Jiang and S. Chang; |
| 2012 | 11 | Visual Tracking Via Adaptive Structural Local Sparse Appearance Model IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we develop a simple yet robust tracking method based on the structural local sparse appearance model. |
X. Jia; H. Lu and M. Yang; |
| 2012 | 12 | Image Denoising: Can Plain Neural Networks Compete With BM3D? IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we attempt to learn this mapping directly with a plain multi layer perceptron (MLP) applied to image patches. |
H. C. Burger; C. J. Schuler and S. Harmeling; |
| 2012 | 13 | Face Alignment By Explicit Shape Regression IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a very efficient, highly accurate, �Explicit Shape Regression� approach for face alignment. |
X. Cao; Y. Wei; F. Wen and J. Sun; |
| 2012 | 14 | Mining Actionlet Ensemble For Action Recognition With Depth Cameras IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, an actionlet ensemble model is learnt to represent each action and to capture the intra-class variance. |
J. Wang; Z. Liu; Y. Wu and J. Yuan; |
| 2012 | 15 | Robust Object Tracking Via Sparsity-based Collaborative Model IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a robust object tracking algorithm using a collaborative model. |
W. Zhong; H. Lu and M. Yang; |
| 2011 | 1 | Real-time Human Pose Recognition In Parts From Single Depth Images IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. |
J. Shotton et al.; |
| 2011 | 2 | Global Contrast Based Salient Region Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. |
M. Cheng; G. Zhang; N. J. Mitra; X. Huang and S. Hu; |
| 2011 | 3 | Unbiased Look At Dataset Bias IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this paper is to take stock of the current state of recognition datasets. |
A. Torralba and A. A. Efros; |
| 2011 | 4 | Action Recognition By Dense Trajectories IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the recent success of dense sampling in image classification, we propose an approach to describe videos by dense trajectories. |
H. Wang; A. Kl�ser; C. Schmid and C. Liu; |
| 2011 | 5 | Face Recognition In Unconstrained Videos With Matched Background Similarity IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we make the following contributions. (a) We present a comprehensive database of labeled videos of faces in challenging, uncontrolled conditions (i.e., `in the wild’), the `YouTube Faces’ database, along with benchmark, pair-matching tests1. |
L. Wolf; T. Hassner and I. Maoz; |
| 2011 | 6 | Fast Cost-volume Filtering For Visual Correspondence And Beyond IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a generic and simple framework comprising three steps: (i) constructing a cost volume (ii) fast cost volume filtering and (iii) winner-take-all label selection. |
C. Rhemann; A. Hosni; M. Bleyer; C. Rother and M. Gelautz; |
| 2011 | 7 | Iterative Quantization: A Procrustean Approach To Learning Binary Codes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a simple and efficient alternating minimization scheme for finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube. |
Y. Gong and S. Lazebnik; |
| 2011 | 8 | Articulated Pose Estimation With Flexible Mixtures-of-parts IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a method for human pose estimation in static images based on a novel representation of part models. |
Y. Yang and D. Ramanan; |
| 2011 | 9 | Learning Hierarchical Invariant Spatio-temporal Features For Action Recognition With Independent Subspace Analysis IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose using unsupervised feature learning as a way to learn features directly from video data. |
Q. V. Le; W. Y. Zou; S. Y. Yeung and A. Y. Ng; |
| 2011 | 10 | Blind Deconvolution Using A Normalized Sparsity Measure IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce a new type of image regularization which gives lowest cost for the true sharp image. |
D. Krishnan; T. Tay and R. Fergus; |
| 2011 | 11 | Localizing Parts Of Faces Using A Consensus Of Exemplars IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel approach to localizing parts in images of human faces. |
P. N. Belhumeur; D. W. Jacobs; D. J. Kriegman and N. Kumar; |
| 2011 | 12 | Entropy Rate Superpixel Segmentation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new objective function for superpixel segmentation. |
M. Liu; O. Tuzel; S. Ramalingam and R. Chellappa; |
| 2011 | 13 | Multicore Bundle Adjustment IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the design and implementation of new inexact Newton type Bundle Adjustment algorithms that exploit hardware parallelism for efficiently solving large scale 3D scene reconstruction problems. |
C. Wu; S. Agarwal; B. Curless and S. M. Seitz; |
| 2011 | 14 | Globally-optimal Greedy Algorithms For Tracking A Variable Number Of Objects IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We analyze the computational problem of multi-object tracking in video sequences. |
H. Pirsiavash; D. Ramanan and C. C. Fowlkes; |
| 2011 | 15 | Sparse Reconstruction Cost For Abnormal Event Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to detect abnormal events via a sparse reconstruction over the normal bases. |
Y. Cong; J. Yuan and J. Liu; |
| 2010 | 1 | SUN Database: Large-scale Scene Recognition From Abbey To Zoo IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. |
J. Xiao; J. Hays; K. A. Ehinger; A. Oliva and A. Torralba; |
| 2010 | 2 | Locality-constrained Linear Coding For Image Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a simple but effective coding scheme called Locality-constrained Linear Coding (LLC) in place of the VQ coding in traditional SPM. |
J. Wang; J. Yang; K. Yu; F. Lv; T. Huang and Y. Gong; |
| 2010 | 3 | Visual Object Tracking Using Adaptive Correlation Filters IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new type of correlation filter, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame. |
D. S. Bolme; J. R. Beveridge; B. A. Draper and Y. M. Lui; |
| 2010 | 4 | Aggregating Local Descriptors Into A Compact Image Representation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address the problem of image search on a very large scale, where three constraints have to be considered jointly: the accuracy of the search, its efficiency, and the memory usage of the representation. |
H. J�gou; M. Douze; C. Schmid and P. P�rez; |
| 2010 | 5 | Context-aware Saliency Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new type of saliency – context-aware saliency – which aims at detecting the image regions that represent the scene. |
S. Goferman; L. Zelnik-Manor and A. Tal; |
| 2010 | 6 | Detecting Text In Natural Scenes With Stroke Width Transform IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel image operator that seeks to find the value of stroke width for each image pixel, and demonstrate its use on the task of text detection in natural images. |
B. Epshtein; E. Ofek and Y. Wexler; |
| 2010 | 7 | Person Re-identification By Symmetry-driven Accumulation Of Local Features IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present an appearance-based method for person re-identification. |
M. Farenzena; L. Bazzani; A. Perina; V. Murino and M. Cristani; |
| 2010 | 8 | Secrets Of Optical Flow Estimation And Their Principles IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To understand the principles behind this phenomenon, we derive a new objective that formalizes the median filtering heuristic. |
D. Sun; S. Roth and M. J. Black; |
| 2010 | 9 | Deconvolutional Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a learning framework where features that capture these mid-level cues spontaneously emerge from image data. |
M. D. Zeiler; D. Krishnan; G. W. Taylor and R. Fergus; |
| 2010 | 10 | Anomaly Detection In Crowded Scenes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel framework for anomaly detection in crowded scenes is presented. |
V. Mahadevan; W. Li; V. Bhalodia and N. Vasconcelos; |
| 2010 | 11 | Discriminative K-SVD For Dictionary Learning In Face Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method to learn an over-complete dictionary that attempts to simultaneously achieve the above two goals. |
Q. Zhang and B. Li; |
| 2010 | 12 | Visual Tracking Decomposition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occur at the same time. |
J. Kwon and K. M. Lee; |
| 2010 | 13 | P-N Learning: Bootstrapping Binary Classifiers By Structural Constraints IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a theory that formulates the conditions under which P-N learning guarantees improvement of the initial classifier and validate it on synthetic and real data. |
Z. Kalal; J. Matas and K. Mikolajczyk; |
| 2010 | 14 | Learning Mid-level Features For Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this paper is threefold. |
Y. Boureau; F. Bach; Y. LeCun and J. Ponce; |
| 2010 | 15 | RASL: Robust Alignment By Sparse And Low-rank Decomposition For Linearly Correlated Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We reduce this extremely challenging optimization problem to a sequence of convex programs that minimize the sum of l1-norm and nuclear norm of the two component matrices, which can be efficiently solved by scalable convex optimization techniques with guaranteed fast convergence. |
Y. Peng; A. Ganesh; J. Wright; W. Xu and Y. Ma; |
| 2009 | 1 | ImageNet: A Large-scale Hierarchical Image Database IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce here a new database called �ImageNet�, a large-scale ontology of images built upon the backbone of the WordNet structure. |
J. Deng; W. Dong; R. Socher; L. Li; Kai Li and Li Fei-Fei; |
| 2009 | 2 | Frequency-tuned Salient Region Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. |
R. Achanta; S. Hemami; F. Estrada and S. Susstrunk; |
| 2009 | 3 | Linear Spatial Pyramid Matching Using Sparse Coding For Image Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we develop an extension of the SPM method, by generalizing vector quantization to sparse coding followed by multi-scale spatial max pooling, and propose a linear SPM kernel based on SIFT sparse codes. |
Jianchao Yang; Kai Yu; Yihong Gong and T. Huang; |
| 2009 | 4 | Learning To Detect Unseen Object Classes By Between-class Attribute Transfer IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we tackle the problem by introducing attribute-based classification. In order to evaluate our method and to facilitate research in this area, we have assembled a new large-scale dataset, �Animals with Attributes�, of over 30,000 animal images that match the 50 classes in Osherson’s classic table of how strongly humans associate 85 semantic attributes with animal classes. |
C. H. Lampert; H. Nickisch and S. Harmeling; |
| 2009 | 5 | Recognizing Linked Events: Searching The Space Of Feasible Explanations IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a set of general move types that is extensible to multiple layers of linkage, and use simulated annealing to find the MAP solution given all observations. |
D. Damen and D. Hogg; |
| 2009 | 6 | Describing Objects By Their Attributes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to shift the goal of recognition from naming to describing. |
A. Farhadi; I. Endres; D. Hoiem and D. Forsyth; |
| 2009 | 7 | Visual Tracking With Online Multiple Instance Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the problem of learning an adaptive appearance model for object tracking. |
B. Babenko; M. Yang and S. Belongie; |
| 2009 | 8 | Abnormal Crowd Behavior Detection Using Social Force Model IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce a novel method to detect and localize abnormal behaviors in crowd videos using Social Force model. |
R. Mehran; A. Oyama and M. Shah; |
| 2009 | 9 | Recognizing Indoor Scenes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a prototype based model that can successfully combine both sources of information. To test our approach we created a dataset of 67 indoor scenes categories (the largest available) covering a wide range of domains. |
A. Quattoni and A. Torralba; |
| 2009 | 10 | Single Image Haze Removal Using Dark Channel Prior IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple but effective image prior – dark channel prior to remove haze from a single input image. |
Kaiming He; Jian Sun and Xiaoou Tang; |
| 2009 | 11 | Sparse Subspace Clustering IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method based on sparse representation (SR) to cluster data drawn from multiple low-dimensional linear or affine subspaces embedded in a high-dimensional space. |
E. Elhamifar and R. Vidal; |
| 2009 | 12 | Pedestrian Detection: A Benchmark IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To continue the rapid rate of innovation, we introduce the Caltech Pedestrian Dataset, which is two orders of magnitude larger than existing datasets. |
P. Dollar; C. Wojek; B. Schiele and P. Perona; |
| 2009 | 13 | Actions In Context IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The contribution of this paper is three-fold: (a) we automatically discover relevant scene classes and their correlation with human actions, (b) we show how to learn selected scene classes from video without manual supervision and (c) we develop a joint framework for action and scene recognition and demonstrate improved recognition of both in natural video. |
M. Marszalek; I. Laptev and C. Schmid; |
| 2009 | 14 | Understanding And Evaluating Blind Deconvolution Algorithms IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this paper is to analyze and evaluate recent blind deconvolution algorithms both theoretically and experimentally. We have collected blur data with ground truth and compared recent algorithms under equal settings. |
A. Levin; Y. Weiss; F. Durand and W. T. Freeman; |
| 2009 | 15 | Pictorial Structures Revisited: People Detection And Articulated Pose Estimation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Numerous models have been proposed over the years and often address different special cases, such as pedestrian detection or upper body pose estimation in TV footage. |
M. Andriluka; S. Roth and B. Schiele; |
| 2008 | 1 | Learning Realistic Human Actions From Movies IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The aim of this paper is to address recognition of natural human actions in diverse and realistic video settings. |
I. Laptev; M. Marszalek; C. Schmid and B. Rozenfeld; |
| 2008 | 2 | A Discriminatively Trained, Multiscale, Deformable Part Model IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a discriminatively trained, multiscale, deformable part model for object detection. |
P. Felzenszwalb; D. McAllester and D. Ramanan; |
| 2008 | 3 | Visibility In Bad Weather From A Single Image IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To resolve the problem, we introduce an automated method that only requires a single input image. |
R. T. Tan; |
| 2008 | 4 | Image Super-resolution As Sparse Representation Of Raw Image Patches IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We approach this problem from the perspective of compressed sensing. |
Jianchao Yang; J. Wright; T. Huang and Yi Ma; |
| 2008 | 5 | Lost In Quantization: Improving Particular Object Retrieval In Large Scale Image Databases IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe how this representation may be incorporated into a standard tf-idf architecture, and how spatial verification is modified in the case of this soft-assignment. We evaluate our method on the standard Oxford Buildings dataset, and introduce a new dataset for evaluation. |
J. Philbin; O. Chum; M. Isard; J. Sivic and A. Zisserman; |
| 2008 | 6 | Action MACH A Spatio-temporal Maximum Average Correlation Height Filter For Action Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce a template-based method for recognizing human actions called action MACH. |
M. D. Rodriguez; J. Ahmed and M. Shah; |
| 2008 | 7 | In Defense Of Nearest-Neighbor Based Image Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a trivial NN-based classifier – NBNN, (Naive-Bayes nearest-neighbor), which employs NN- distances in the space of the local image descriptors (and not in the space of images). |
O. Boiman; E. Shechtman and M. Irani; |
| 2008 | 8 | Semantic Texton Forests For Image Categorization And Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose semantic texton forests, efficient and powerful new low-level features. |
J. Shotton; M. Johnson and R. Cipolla; |
| 2008 | 9 | Image Super-resolution Using Gradient Profile Prior IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an image super-resolution approach using a novel generic image prior – gradient profile prior, which is a parametric prior describing the shape and the sharpness of the image gradients. |
Jian Sun; Zongben Xu and Heung-Yeung Shum; |
| 2008 | 10 | Privacy Preserving Crowd Monitoring: Counting People Without People Models Or Tracking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a privacy-preserving system for estimating the size of inhomogeneous crowds, composed of pedestrians that travel in different directions, without using explicit object segmentation or tracking. |
A. B. Chan; Zhang-Sheng John Liang and N. Vasconcelos; |
| 2008 | 11 | Classification Using Intersection Kernel Support Vector Machines Is Efficient IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For a class of kernels we show that one can do this much more efficiently. |
S. Maji; A. C. Berg and J. Malik; |
| 2008 | 12 | Robust Higher Order Potentials For Enforcing Label Consistency IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner. |
P. Kohli; L. Ladicky and P. H. S. Torr; |
| 2008 | 13 | Global Data Association For Multi-object Tracking Using Network Flows IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a network flow based optimization method for data association needed for multiple object tracking. |
Li Zhang; Yuan Li and R. Nevatia; |
| 2008 | 14 | People-tracking-by-detection And People-detection-by-tracking IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we combine the advantages of both detection and tracking in a single framework. |
M. Andriluka; S. Roth and B. Schiele; |
| 2008 | 15 | IM2GPS: Estimating Geographic Information From A Single Image IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple algorithm for estimating a distribution over geographic locations from a single image using a purely data-driven scene matching approach. |
J. Hays and A. A. Efros; |
| 2007 | 1 | Saliency Detection: A Spectral Residual Approach IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a simple method for the visual saliency detection. |
X. Hou and L. Zhang; |
| 2007 | 2 | Object Retrieval With Large Vocabularies And Fast Spatial Matching IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a large-scale object retrieval system. |
J. Philbin; O. Chum; M. Isard; J. Sivic and A. Zisserman; |
| 2007 | 3 | Accurate, Dense, And Robust Multi-View Stereopsis IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a novel algorithm for calibrated multi-view stereopsis that outputs a (quasi) dense set of rectangular patches covering the surfaces visible in the input images. |
Y. Furukawa and J. Ponce; |
| 2007 | 4 | Learning To Detect A Salient Object IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a set of novel features including multi-scale contrast, center-surround histogram, and color spatial distribution to describe a salient object locally, regionally, and globally. We also constructed a large image database containing tens of thousands of carefully labeled images by multiple users. |
T. Liu; J. Sun; N. Zheng; X. Tang and H. Shum; |
| 2007 | 5 | Fisher Kernels On Visual Vocabularies For Image Categorization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to apply this framework to image categorization where the input signals are images and where the underlying generative model is a visual vocabulary: a Gaussian mixture model which approximates the distribution of low-level features in images. |
F. Perronnin and C. Dance; |
| 2007 | 6 | Evaluation Of Cost Functions For Stereo Matching IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we evaluate the insensitivity of different matching costs with respect to radiometric variations of the input images. |
H. Hirschmuller and D. Scharstein; |
| 2007 | 7 | Unsupervised Learning Of Invariant Feature Hierarchies With Applications To Object Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. |
M. Ranzato; F. J. Huang; Y. Boureau and Y. LeCun; |
| 2007 | 8 | Matching Local Self-Similarities Across Images And Videos IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach for measuring similarity between visual entities (images or videos) based on matching internal self-similarities. |
E. Shechtman and M. Irani; |
| 2007 | 9 | Learning Conditional Random Fields For Stereo IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we seek to replace such heuristics with explicit probabilistic models of disparities and intensities learned from real images. |
D. Scharstein and C. Pal; |
| 2007 | 10 | Implicit Active Contours Driven By Local Binary Fitting Energy IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a region-based active contour model that is able to utilize image information in local regions. |
C. Li; C. Kao; J. C. Gore and Z. Ding; |
| 2007 | 11 | Spatial-Depth Super Resolution For Range Images IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new post-processing step to enhance the resolution of range images. |
Q. Yang; R. Yang; J. Davis and D. Nister; |
| 2007 | 12 | Optimal Step Nonrigid ICP Algorithms For Surface Registration IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an algorithm using a locally affine regularisation which assigns an affine transformation to each vertex and minimises the difference in the transformation of neighbouring vertices. |
B. Amberg; S. Romdhani and T. Vetter; |
| 2007 | 13 | City-Scale Location Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular we show that by carefully selecting the vocabulary using the most informative features, retrieval performance is significantly improved, allowing us to increase the number of database images by a factor of 10. |
G. Schindler; M. Brown and R. Szeliski; |
| 2007 | 14 | A Benchmark For The Comparison Of 3-D Motion Segmentation Algorithms IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we compare four 3D motion segmentation algorithms for affine cameras on a benchmark of 155 motion sequences of checkerboard, traffic, and articulated scenes. |
R. Tron and R. Vidal; |
| 2007 | 15 | A Lagrangian Particle Dynamics Approach For Crowd Flow Segmentation And Stability Analysis IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a framework in which Lagrangian particle dynamics is used for the segmentation of high density crowd flows and detection of flow instabilities. |
S. Ali and M. Shah; |
| 2006 | 1 | Beyond Bags Of Features: Spatial Pyramid Matching For Recognizing Natural Scene Categories IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. |
S. Lazebnik; C. Schmid and J. Ponce; |
| 2006 | 2 | Dimensionality Reduction By Learning An Invariant Mapping IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method – called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) – for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. |
R. Hadsell; S. Chopra and Y. LeCun; |
| 2006 | 3 | Scalable Recognition With A Vocabulary Tree IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The vocabulary tree allows a larger and more discriminatory vocabulary to be used efficiently, which we show experimentally leads to a dramatic improvement in retrieval quality. |
D. Nister and H. Stewenius; |
| 2006 | 4 | A Comparison And Evaluation Of Multi-View Stereo Reconstruction Algorithms IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a quantitative comparison of several multi-view stereo reconstruction algorithms. |
S. M. Seitz; B. Curless; J. Diebel; D. Scharstein and R. Szeliski; |
| 2006 | 5 | Robust Fragments-based Tracking Using The Integral Histogram IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel algorithm (which we call Frag- Track) for tracking an object in a video sequence. |
A. Adam; E. Rivlin and I. Shimshoni; |
| 2006 | 6 | SVM-KNN: Discriminative Nearest Neighbor Classification For Visual Category Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a hybrid of these two methods which deals naturally with the multiclass setting, has reasonable computational complexity both in training and at run time, and yields excellent results in practice. |
Hao Zhang; A. C. Berg; M. Maire and J. Malik; |
| 2006 | 7 | On-line Boosting And Vision IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a novel on-line AdaBoost feature selection method. |
H. Grabner and H. Bischof; |
| 2006 | 8 | Putting Objects In Perspective IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. |
D. Hoiem; A. A. Efros and M. Hebert; |
| 2006 | 9 | A Visual Vocabulary For Flower Classification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate to what extent �bag of visual words� models can be used to distinguish categories which have significant visual similarity. |
M. -. Nilsback and A. Zisserman; |
| 2006 | 10 | Using Multiple Segmentations To Discover Objects And Their Extent In Image Collections IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. |
B. C. Russell; W. T. Freeman; A. A. Efros; J. Sivic and A. Zisserman; |
| 2006 | 11 | The Design Of High-Level Features For Photo Quality Assessment IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a principled method for designing high level features forphoto quality assessment. |
Yan Ke; Xiaoou Tang and Feng Jing; |
| 2006 | 12 | Stereo Matching With Color-Weighted Correlation, Hierachical Belief Propagation And Occlusion Handling IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we formulate an algorithm for the stereo matching problem with careful handling of disparity, discontinuity and occlusion. |
Qyngxiong Yang; Liang Wang; Ruigang Yang; H. Stewenius and D. Nister; |
| 2006 | 13 | Fast Human Detection Using A Cascade Of Histograms Of Oriented Gradients IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We integrate the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system. |
Qiang Zhu; Mei-Chen Yeh; Kwang-Ting Cheng and S. Avidan; |
| 2006 | 14 | CSIFT: A SIFT Descriptor With Color Invariant Characteristics IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Instead of using the gray space to represent the input image, the proposed approach builds the SIFT descriptors in a color invariant space. |
A. E. Abdel-Hakim and A. A. Farag; |
| 2006 | 15 | Covariance Tracking Using Model Update Based On Lie Algebra IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a simple and elegant algorithm to track nonrigid objects using a covariance based object description and a Lie algebra based update mechanism. |
F. Porikli; O. Tuzel and P. Meer; |
| 2005 | 1 | Histograms Of Oriented Gradients For Human Detection IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds. |
N. Dalal and B. Triggs; |
| 2005 | 2 | A Non-local Algorithm For Image Denoising IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new measure, the method noise, to evaluate and compare the performance of digital image denoising methods. |
A. Buades; B. Coll and J. -. Morel; |
| 2005 | 3 | Learning A Similarity Metric Discriminatively, With Application To Face Verification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method for training a similarity metric from data. |
S. Chopra; R. Hadsell and Y. LeCun; |
| 2005 | 4 | A Bayesian Hierarchical Model For Learning Natural Scene Categories IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel approach to learn and recognize natural scene categories. |
L. Fei-Fei and P. Perona; |
| 2005 | 5 | Overview Of The Face Recognition Grand Challenge IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the challenge problem, data corpus, and presents baseline performance and preliminary results on natural statistics of facial imagery. |
P. J. Phillips et al.; |
| 2005 | 6 | Level Set Evolution Without Re-initialization: A New Variational Formulation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a new variational formulation for geometric active contours that forces the level set function to be close to a signed distance function, and therefore completely eliminates the need of the costly re-initialization procedure. |
Chunming Li; Chenyang Xu; Changfeng Gui and M. D. Fox; |
| 2005 | 7 | Ensemble Tracking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider tracking as a binary classification problem, where an ensemble of weak classifiers is trained online to distinguish between the object and the background. |
S. Avidan; |
| 2005 | 8 | Matching With PROSAC – Progressive Sample Consensus IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new robust matching method is proposed. |
O. Chum and J. Matas; |
| 2005 | 9 | Fields Of Experts: A Framework For Learning Image Priors IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. |
S. Roth and M. J. Black; |
| 2005 | 10 | Shape Matching And Object Recognition Using Low Distortion Correspondences IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. |
A. C. Berg; T. L. Berg and J. Malik; |
| 2005 | 11 | Object Recognition With Features Inspired By Visual Cortex IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a novel set of features for robust object recognition. |
T. Serre; L. Wolf and T. Poggio; |
| 2005 | 12 | Pedestrian Detection In Crowded Scenes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. |
B. Leibe; E. Seemann and B. Schiele; |
| 2005 | 13 | ARTag, A Fiducial Marker System Using Digital Techniques IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Fiducial marker systems consist of patterns that are mounted in the environment and automatically detected in digital camera images using an accompanying detection algorithm. |
M. Fiala; |
| 2005 | 14 | Accurate And Efficient Stereo Processing By Semi-global Matching And Mutual Information IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper considers the objectives of accurate stereo matching, especially at object boundaries, robustness against recording or illumination changes and efficiency of the calculation. |
H. Hirschmuller; |
| 2005 | 15 | Integral Histogram: A Fast Way To Extract Histograms In Cartesian Spaces IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel method, which we refer as an integral histogram, to compute the histograms of all possible target regions in a Cartesian data space. |
F. Porikli; |
| 2004 | 1 | PCA-SIFT: A More Distinctive Representation For Local Image Descriptors IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper examines (and improves upon) the local image descriptor used by SIFT. |
Yan Ke and R. Sukthankar; |
| 2004 | 2 | Super-resolution Through Neighbor Embedding IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel method for solving single-image super-resolution problems. |
Hong Chang; Dit-Yan Yeung and Yimin Xiong; |
| 2004 | 3 | Visual Odometry IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a system that estimates the motion of a stereo head or a single moving camera based on video input. |
D. Nister; O. Naroditsky and J. Bergen; |
| 2004 | 4 | Efficient Belief Propagation For Early Vision IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present new algorithmic techniques that substantially improve the running time of the belief propagation approach. |
P. F. Felzenszwalb and D. R. Huttenlocher; |
| 2004 | 5 | Learning Methods For Generic Object Recognition With Invariance To Pose And Lighting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: We assess the applicability of several popular learning methods for the problem of recognizing generic visual categories with invariance to pose, lighting, and surrounding … |
Y. LeCun; Fu Jie Huang and L. Bottou; |
| 2004 | 6 | Multiscale Conditional Random Fields For Image Labeling IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an approach to include contextual features for labeling images, in which each pixel is assigned to one of a finite set of labels. |
Xuming He; R. S. Zemel and M. A. Carreira-Perpinan; |
| 2004 | 7 | Unsupervised Learning Of Image Manifolds By Semidefinite Programming IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new solution to this problem based on semidefinite programming. |
K. Q. Weinberger and L. K. Saul; |
| 2004 | 8 | Multiple Bernoulli Relevance Models For Image And Video Annotation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The word probabilities are estimated using a multiple Bernoulli model and the image feature probabilities using a non-parametric kernel density estimate. |
S. L. Feng; R. Manmatha and V. Lavrenko; |
| 2004 | 9 | Detecting And Reading Text In Natural Scenes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper gives an algorithm for detecting and reading text in natural images. We first obtain a dataset of city images taken by blind and normally sighted subjects. |
Xiangrong Chen and A. L. Yuille; |
| 2004 | 10 | Motion-based Background Subtraction Using Adaptive Kernel Density Estimation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new method for the modeling and subtraction of such scenes. |
A. Mittal and N. Paragios; |
| 2004 | 11 | Sharing Features: Efficient Boosting Procedures For Multiclass Object Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a multi-class boosting procedure (joint boosting) that reduces both the computational and sample complexity, by finding common features that can be shared across the classes. |
A. Torralba; K. P. Murphy and W. T. Freeman; |
| 2004 | 12 | Is Bottom-up Attention Useful For Object Recognition? IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate empirically to what extent pure bottom-up attention can extract useful information about the location, size and shape of objects from images and demonstrate how this information can be utilized to enable unsupervised learning of objects from unlabeled images. |
U. Rutishauser; D. Walther; C. Koch and P. Perona; |
| 2004 | 13 | Recovering Human Body Configurations: Combining Segmentation And Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this work is to detect a human figure image and localize his joints and limbs along with their associated pixel masks. |
G. Mori; Xiaofeng Ren; A. A. Efros and J. Malik; |
| 2004 | 14 | Detecting Unusual Activity In Video IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an unsupervised technique for detecting unusual activity in a large video set using many simple features. |
Hua Zhong; Jianbo Shi and M. Visontai; |
| 2004 | 15 | Detection And Removal Of Rain From Videos IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The techniques described in this paper can be used in a wide range of applications including video surveillance, vision based navigation, video/movie editing and video indexing/retrieval. |
K. Garg and S. K. Nayar; |
| 2003 | 1 | A Performance Evaluation Of Local Descriptors IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we compare the performance of interest point descriptors. |
K. Mikolajczyk and C. Schmid; |
| 2003 | 2 | Object Class Recognition By Unsupervised Scale-invariant Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. |
R. Fergus; P. Perona and A. Zisserman; |
| 2003 | 3 | High-accuracy Stereo Depth Maps Using Structured Light IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a method for acquiring high-complexity stereo image pairs with pixel-accurate correspondence information using structured light. |
D. Scharstein and R. Szeliski; |
| 2003 | 4 | An Efficient Solution To The Five-point Relative Pose Problem IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An efficient algorithmic solution to the classical five-point relative pose problem is presented. |
D. Nister; |
| 2003 | 5 | Simultaneous Structure And Texture Image Inpainting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An algorithm for the simultaneous filling-in of texture and structure in regions of missing image information is presented. |
M. Bertalmio; L. Vese; G. Sapiro and S. Osher; |
| 2003 | 6 | Object Removal By Exemplar-based Inpainting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a novel and efficient algorithm that combines the advantages of these two approaches. |
A. Criminisi; P. Perez and K. Toyama; |
| 2003 | 7 | Generalized Principal Component Analysis (GPCA) IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an algebraic geometric approach to the problem of estimating a mixture of linear subspaces from sample data points, the so-called generalized principal component analysis (GPCA) problem. |
R. Vidal; Yi Ma and S. Sastry; |
| 2003 | 8 | Mean-shift Blob Tracking Through Scale Space IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We adapt Lindeberg’s (1998) theory of feature scale selection based on local maxima of differential scale-space filters to the problem of selecting kernel scale for mean-shift blob tracking. |
R. T. Collins; |
| 2003 | 9 | Analyzing Appearance And Contour Based Methods For Object Categorization IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to compare different methods we present a new database specifically tailored to the task of object categorization. |
B. Leibe and B. Schiele; |
| 2003 | 10 | Recognizing Objects In Adversarial Clutter: Breaking A Visual CAPTCHA IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we explore object recognition in clutter. |
G. Mori and J. Malik; |
| 2003 | 11 | Vector-valued Image Regularization With PDE’s: A Common Framework For Different Applications IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: From the study of existing formalisms, we propose a unifying framework based on a very local interpretation of the regularization processes. |
D. Tschumperle and R. Deriche; |
| 2003 | 12 | Word Image Matching Using Dynamic Time Warping IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an algorithm for matching handwritten words in noisy historical documents. |
T. M. Rath and R. Manmatha; |
| 2003 | 13 | Nonparametric Belief Propagation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Thus, NBP extends particle filtering methods to the more general vision problems that graphical models can describe. |
E. B. Sudderth; A. T. Ihler; W. T. Freeman and A. S. Willsky; |
| 2003 | 14 | Clustering Appearances Of Objects Under Varying Illumination Conditions IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce two appearance-based methods for clustering a set of images of 3D (three-dimensional) objects, acquired under varying illumination conditions, into disjoint subsets corresponding to individual objects. |
J. Ho; Ming-Husang Yang; Jongwoo Lim; Kuang-Chih Lee and D. Kriegman; |
| 2003 | 15 | Video-based Face Recognition Using Probabilistic Appearance Manifolds IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a method to model and recognize human faces in video sequences. |
Kuang-Chih Lee; J. Ho; Ming-Hsuan Yang and D. Kriegman; |
| 2001 | 1 | Rapid Object Detection Using A Boosted Cascade Of Simple Features IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. |
P. Viola and M. Jones; |
| 2001 | 2 | Robust Online Appearance Models For Visual Tracking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a framework for learning robust, adaptive appearance models to be used for motion-based tracking of natural objects. |
A. D. Jepson; D. J. Fleet and T. R. El-Maraghi; |
| 2001 | 3 | Navier-stokes, Fluid Dynamics, And Image And Video Inpainting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a class of automated methods for digital inpainting. |
M. Bertalmio; A. L. Bertozzi and G. Sapiro; |
| 2001 | 4 | A Bayesian Approach To Digital Matting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element. |
Yung-Yu Chuang; B. Curless; D. H. Salesin and R. Szeliski; |
| 2001 | 5 | Support Vector Tracking IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. |
S. Avidan; |
| 2001 | 6 | Instant Dehazing Of Images Using Polarization IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach to easily remove the effects of haze from images. |
Y. Y. Schechner; S. G. Narasimhan and S. K. Nayar; |
| 2001 | 7 | Learning Spatially Localized, Parts-based Representation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel method, called local non-negative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns. |
S. Z. Li; Xin Wen Hou; Hong Jiang Zhang and Qian Sheng Cheng; |
| 2001 | 8 | On The Individuality Fingerprints IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address the problem of fingerprint individuality by quantifying the amount of information available in minutiae points to establish a correspondence between two fingerprint images. |
S. Pankanti; S. Prabhakar and A. K. Jain; |
| 2001 | 9 | Local Feature View Clustering For 3D Object Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a method for combining multiple images of a 3D object into a single model representation. |
D. G. Lowe; |
| 2001 | 10 | Simultaneous Linear Estimation Of Multiple View Geometry And Lens Distortion IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This is achieved by (1) changing from the standard radial-lens model to another which (as we show) has equivalent power, but which takes a simpler form in homogeneous coordinates, and (2) expressing fundamental matrix estimation as a quadratic eigenvalue problem (QEP), for which efficient algorithms are well known. |
A. W. Fitzgibbon; |
| 2001 | 11 | 3D Simultaneous Localisation And Map-building Using Active Vision For A Robot Moving On Undulating Terrain IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a real-time EKF-based-SLAM system permitting unconstrained 3D localisation, and in particular develop models for the motion of a wheeled robot in the presence of unknown slope variations. |
A. J. Davison and N. Kita; |
| 2001 | 12 | Event-based Analysis Of Video IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on this, we design a simple statistical distance measure between video sequences (possibly of different lengths) based on their behavioral content. |
L. Zelnik-Manor and M. Irani; |
| 2001 | 13 | Robust Super-resolution IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A robust approach for super-resolution is, presented, which is especially valuable in the presence of outliers. |
A. Zomet; A. Rav-Acha and S. Peleg; |
| 2001 | 14 | Equivalence And Efficiency Of Image Alignment Algorithms IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A very efficient algorithm was proposed by Hager and Belhumeur (1998) using the additive approach that unfortunately can only be applied to a very restricted class of warps. |
S. Baker and I. Matthews; |
| 2001 | 15 | Handling Occlusions In Dense Multi-view Stereo IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose some novel techniques to deal with this problem. |
Sing Bing Kang; R. Szeliski and Jinxiang Chai; |
| 2000 | 1 | Real-time Tracking Of Non-rigid Objects Using Mean Shift IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new method for real time tracking of non-rigid objects seen from a moving camera is proposed. |
D. Comaniciu; V. Ramesh and P. Meer; |
| 2000 | 2 | Limits On Super-resolution And How To Break Them IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We therefore propose an algorithm that learns recognition-based priors for specific classes of scenes, the use of which gives far better super-resolution results for both faces and text. |
S. Baker and T. Kanade; |
| 2000 | 3 | Learning To Recognize Objects IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We evaluate this approach an a large scale experimental study in which the SNoW learning architecture is used to learn representations for the 100 objects in the Columbia Object Image Database (COIL-100). |
D. Roth; Ming-Hsuan Yang and N. Ahuja; |
| 2000 | 4 | A Statistical Method For 3D Object Detection Applied To Faces And Cars IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe a statistical method for 3D object detection. |
H. Schneiderman and T. Kanade; |
| 2000 | 5 | Statistical Shape Influence In Geodesic Active Contours IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel method of incorporating shape information into the image segmentation process is presented. |
M. E. Leventon; W. E. L. Grimson and O. Faugeras; |
| 2000 | 6 | Articulated Body Motion Capture By Annealed Particle Filtering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The principal contribution of the paper is the development of a modified particle filter for search in high dimensional configuration spaces. |
J. Deutscher; A. Blake and I. Reid; |
| 2000 | 7 | Recovering Non-rigid 3D Shape From Image Streams IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel technique based on a non-rigid model, where the 3D shape in each frame is a linear combination of a set of basis shapes. |
C. Bregler; A. Hertzmann and H. Biermann; |
| 2000 | 8 | Shape Descriptors For Non-rigid Shapes With A Single Closed Contour IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we report on the MPEG-7 Core Experiment CE-Shape. |
L. J. Latecki; R. Lakamper and T. Eckhardt; |
| 2000 | 9 | Chromatic Framework For Vision In Bad Weather IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop a geometric framework for analyzing the chromatic effects of atmospheric scattering. |
S. G. Narasimhan and S. K. Nayar; |
| 2000 | 10 | Reliable Feature Matching Across Widely Separated Views IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints. |
A. Baumberg; |
| 2000 | 11 | Boosting Image Retrieval IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. |
K. Tieu and P. Viola; |
| 2000 | 12 | High Dynamic Range Imaging: Spatially Varying Pixel Exposures IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a very simple method for significantly enhancing the dynamic range of virtually any imaging system. |
S. K. Nayar and T. Mitsunaga; |
| 2000 | 13 | A New Algorithm For Non-rigid Point Matching IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new robust point matching algorithm (RPM) that can jointly estimate the correspondence and non-rigid transformations between two point-sets that may be of different sizes. |
Haili Chui and A. Rangarajan; |
| 2000 | 14 | A Real Time System For Robust 3D Voxel Reconstruction Of Human Motions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a multi-PC/camera system that can perform 3D reconstruction and ellipsoid fitting of moving humans in real time. |
G. K. M. Cheung; T. Kanade; J. -. Bouguet and M. Holler; |
| 2000 | 15 | Learning From One Example Through Shared Densities On Transforms IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We define a process called congealing in which elements of a dataset (images) are brought into correspondence with each other jointly, producing a data-defined model. |
E. G. Miller; N. E. Matsakis and P. A. Viola; |
| 1999 | 1 | Adaptive Background Mixture Models For Real-time Tracking IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The numerous approaches to this problem differ in the type of background model used and the procedure used to update the model. |
C. Stauffer and W. E. L. Grimson; |
| 1999 | 2 | Statistical Color Models With Application To Skin Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe the construction of color models for skin and non-skin classes from a dataset of nearly 1 billion labeled pixels. |
M. J. Jones and J. M. Rehg; |
| 1999 | 3 | Radiometric Self Calibration IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A simple algorithm is described that computes the radiometric response function of an imaging system, from images of an arbitrary scene taken using different exposures. |
T. Mitsunaga and S. K. Nayar; |
| 1999 | 4 | Color Image Segmentation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented. |
Yining Deng; B. S. Manjunath and H. Shin; |
| 1999 | 5 | On Plane-based Camera Calibration: A General Algorithm, Singularities, Applications IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a general algorithm for plane-based calibration that can deal with arbitrary numbers of views and calibration planes. |
P. F. Sturm and S. J. Maybank; |
| 1999 | 6 | Statistics Of Natural Images And Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These make possible precise and intensive statistical studies of the local nature of images. |
Jinggang Huang and D. Mumford; |
| 1999 | 7 | Computing Rectifying Homographies For Stereo Vision IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel technique for image rectification based on geometrically well defined criteria such that image distortion due to rectification is minimized. |
C. Loop and Zhengyou Zhang; |
| 1999 | 8 | Edge Detector Evaluation Using Empirical ROC Curves IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method is demonstrated to evaluate edge detector performance using receiver operating characteristic curves. |
K. Bowyer; C. Kranenburg and S. Dougherty; |
| 1999 | 9 | A Multiple Hypothesis Approach To Figure Tracking IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a probabilistic multiple-hypothesis framework for tracking highly articulated objects. |
Tat-Jen Cham and J. M. Rehg; |
| 1999 | 10 | Bayesian Multi-camera Surveillance IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a Bayesian formalization of this task, where the optimal solution is the set of object paths with the highest posterior probability given the observed data. |
V. Kettnaker and R. Zabih; |
| 1999 | 11 | Automatic Reconstruction Of Piecewise Planar Models From Multiple Views IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new method is described for automatically reconstructing 3D planar faces from multiple images of a scene. |
C. Baillard and A. Zisserman; |
| 1999 | 12 | Using The CONDENSATION Algorithm For Robust, Vision-based Mobile Robot Localization IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a novel, vision-based localization method based on the CONDENSATION algorithm, a Bayesian filtering method that uses a sampling-based density representation. |
F. Dellaert; W. Burgard; D. Fox and S. Thrun; |
| 1999 | 13 | Non-metric Calibration Of Wide-angle Lenses And Polycameras IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a method for recovering the distortion parameters without the use of any calibration objects. |
R. Swarninathan and S. K. Nayar; |
| 1999 | 14 | Detecting And Tracking Moving Objects For Video Surveillance IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address the problem of detection and tracking of moving objects in a video stream obtained from a moving airborne platform. |
I. Cohen and G. Medioni; |
| 1999 | 15 | Stereo Panorama With A Single Camera IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Full panoramic images, covering 360 degrees, can be created either by using panoramic cameras or by mosaicing together many regular images. Creating panoramic views in stereo, … |
S. Peleg and M. Ben-Ezra; |
| 1998 | 1 | Elliptical Head Tracking Using Intensity Gradients And Color Histograms IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An algorithm for tracking a person’s head is presented. |
S. Birchfield; |
| 1998 | 2 | Tracking People With Twists And Exponential Maps IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the use of a novel mathematical technique, the product of exponential maps and twist motions, and its integration into a differential motion estimation. |
C. Bregler and J. Malik; |
| 1998 | 3 | Using Adaptive Tracking To Classify And Monitor Activities In A Site IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a vision system that monitors activity in a site over extended periods of time. |
W. E. L. Grimson; C. Stauffer; R. Romano and L. Lee; |
| 1998 | 4 | Integrated Person Tracking Using Stereo, Color, And Pattern Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach to real-time person tracking in crowded and/or unknown environments using multi-modal integration. |
T. Darrell; G. Gordon; M. Harville and J. Woodfill; |
| 1998 | 5 | Markov Random Fields With Efficient Approximations IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we focus on MRFs with two-valued clique potentials, which form a generalized Potts model. |
Y. Boykov; O. Veksler and R. Zabih; |
| 1998 | 6 | Rotation Invariant Neural Network-Based Face Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View |
H. A. Rowley; S. Baluja and T. Kanade; |
| 1998 | 7 | Probabilistic Modeling Of Local Appearance And Spatial Relationships For Object Recognition IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe an algorithm for object recognition that explicitly models and estimated the posterior probability function, P(object/image). |
H. Schneiderman and T. Kanade; |
| 1998 | 8 | Metric Rectification For Perspective Images Of Planes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe the geometry constraints and algorithmic implementation for metric rectification of planes. |
D. Liebowitz and A. Zisserman; |
| 1998 | 9 | Mosaics Of Scenes With Moving Objects IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a complete system for creating visually pleasing mosaics in the presence of moving objects. |
J. Davis; |
| 1998 | 10 | Image Segmentation Using Local Variation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new graph-theoretic approach to the problem of image segmentation. |
P. F. Felzenszwalb and D. P. Huttenlocher; |
| 1998 | 11 | Illumination Cones For Recognition Under Variable Lighting: Faces IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents an appearance-based method for modeling the variability due to illumination in the images of objects. |
A. S. Georghiades; D. J. Kriegman and P. N. Belhurneur; |
| 1998 | 12 | Automated Mosaicing With Super-resolution Zoom IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe mosaicing for a sequence of images acquired by a camera rotating about its centre. |
D. Capel and A. Zisserman; |
| 1998 | 13 | A Layered Approach To Stereo Reconstruction IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a framework for extracting structure from stereo which represents the scene as a collection of approximately planar layers. |
S. Baker; R. Szeliski and P. Anandan; |
| 1998 | 14 | Segmentation By Grouping Junctions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method for segmenting gray-value images. |
H. Ishikawa and D. Geiger; |
| 1998 | 15 | Video Scene Segmentation Via Continuous Video Coherence IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present three novel high-level segmentation results derived from these considerations, some of which are analogous to those involved in the perception of the structure of music. |
J. R. Kender and Boon-Lock Yeo; |
| 1997 | 1 | Normalized Cuts And Image Segmentation IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel approach for solving the perceptual grouping problem in vision. |
Jianbo Shi and J. Malik; |
| 1997 | 2 | The FERET Evaluation Methodology For Face-recognition Algorithms IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems. … |
P. J. Phillips; Hyeonjoon Moon; P. Rauss and S. A. Rizvi; |
| 1997 | 3 | Training Support Vector Machines: An Application To Face Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a decomposition algorithm that guarantees global optimality, and can be used to train SVM’s over very large data sets. |
E. Osuna; R. Freund and F. Girosit; |
| 1997 | 4 | A Four-step Camera Calibration Procedure With Implicit Image Correction IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a four-step calibration procedure that is an extension to the two-step method. |
J. Heikkila and O. Silven; |
| 1997 | 5 | Image Indexing Using Color Correlograms IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We define a new image feature called the color correlogram and use it for image indexing and comparison. |
Jing Huang; S. R. Kumar; M. Mitra; Wei-Jing Zhu and R. Zabih; |
| 1997 | 6 | Reflectance And Texture Of Real-world Surfaces IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we investigate the visual appearance of real-world surfaces and the dependence of appearance on imaging conditions. |
K. J. Dana; S. K. Nayar; B. van Ginneken and J. J. Koenderink; |
| 1997 | 7 | Coupled Hidden Markov Models For Complex Action Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying two-handed actions. |
M. Brand; N. Oliver and A. Pentland; |
| 1997 | 8 | Photorealistic Scene Reconstruction By Voxel Coloring IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel scene reconstruction technique is presented, different from previous approaches in its ability to cope with large changes in visibility and its modeling of intrinsic scene color and texture information. |
S. M. Seitz and C. R. Dyer; |
| 1997 | 9 | Shape Indexing Using Approximate Nearest-neighbour Search In High-dimensional Spaces IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we show that a new variant of the k-d tree search algorithm makes indexing in higher-dimensional spaces practical. |
J. S. Beis and D. G. Lowe; |
| 1997 | 10 | Gradient Vector Flow: A New External Force For Snakes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper develops a new external force for active contours, largely solving both problems. |
Chenyang Xu and J. L. Prince; |
| 1997 | 11 | Pedestrian Detection Using Wavelet Templates IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes. |
M. Oren; C. Papageorgiou; P. Sinha; E. Osuna and T. Poggio; |
| 1997 | 12 | Robust Analysis Of Feature Spaces: Color Image Segmentation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A general technique for the recovery of significant image features is presented. |
D. Comaniciu and P. Meer; |
| 1997 | 13 | Learning And Recognizing Human Dynamics In Video Sequences IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a probabilistic decomposition of human dynamics at multiple abstractions, and shows how to propagate hypotheses across space, time, and abstraction levels. |
C. Bregler; |
| 1997 | 14 | Catadioptric Omnidirectional Camera IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Conventional video cameras have limited fields of view that make them restrictive in a variety of vision applications. There are several ways to enhance the field of view of an … |
S. K. Nayar; |
| 1997 | 15 | The Bas-relief Ambiguity IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents an explanation of this phenomena, showing that the ambiguity in determining the relief of an object is not confined to bas-relief sculpture but is implicit in the determination of the structure of any object. |
P. N. Belhumeur; D. J. Kriegman and A. L. Yuille; |
| 1996 | 1 | Neural Network-based Face Detection IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a neural network-based face detection system. |
H. A. Rowley; S. Baluja and T. Kanade; |
| 1996 | 2 | Edge Detection And Ridge Detection With Automatic Scale Selection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This article presents a systematic methodology for addressing this problem. |
T. Lindeberg; |
| 1996 | 3 | Combination Of Multiple Classifiers Using Local Accuracy Estimates IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a method for combining classifiers that use estimates of each individual classifier’s local accuracy in small regions of feature space surrounding an unknown test sample. |
K. Woods; K. Bowyer and W. P. Kegelmeyer; |
| 1996 | 4 | 3-D Model-based Tracking Of Humans In Action: A Multi-view Approach IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a vision system for the 3-D model-based tracking of unconstrained human movement. |
D. M. Gavrila and L. S. Davis; |
| 1996 | 5 | Global Minimum For Active Contour Models: A Minimal Path Approach IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new boundary detection approach for shape modeling is presented. |
L. D. Cohen and R. Kimmel; |
| 1996 | 6 | A Stereo Machine For Video-rate Dense Depth Mapping And Its New Applications IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have developed a video-rate stereo machine that has the capability of generating a dense depth map at the video rate. |
T. Kanade; A. Yoshida; K. Oda; H. Kano and M. Tanaka; |
| 1996 | 7 | A Space-sweep Approach To True Multi-image Matching IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The term true multi-image matching is introduced to describe techniques that make full and efficient use of the geometric relationships between multiple images and the scene. |
R. T. Collins; |
| 1996 | 8 | Comparison Of Edge Detectors: A Methodology And Initial Study IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The purpose of this paper is to describe a new (to computer vision) experimental framework which allows us to make quantitative comparisons using subjective ratings made by people. |
M. Heath; S. Sarkar; T. Sanocki and K. Bowyer; |
| 1996 | 9 | What Is The Set Of Images Of An Object Under All Possible Lighting Conditions? IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider only the set of images of an object under variable illumination (including multiple, extended light sources and attached shadows). |
P. N. Belhumeur and D. J. Kriegman; |
| 1996 | 10 | Interactive Learning With A Society Of Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes an approach for integrating a large number of context-dependent features into a semi-automated tool. |
T. P. Minka and R. W. Picard; |
| 1996 | 11 | Texture Features And Learning Similarity IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper addresses two important issues related to texture pattern retrieval: feature extraction and similarity search. |
W. Y. Ma and B. S. Manjunath; |
| 1996 | 12 | Factorization Methods For Projective Structure And Motion IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a family of factorization-based algorithms that recover 3D projective structure and motion from multiple uncalibrated perspective images of 3D points and lines. |
B. Triggs; |
| 1996 | 13 | Feature-based Face Recognition Using Mixture-distance IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The mixture-distance technique we introduce achieves a recognition rate of 95% on a database of 685 people in which each face is represented by 30 measured distances. |
I. J. Cox; J. Ghosn and P. N. Yianilos; |
| 1996 | 14 | A Unified Mixture Framework For Motion Segmentation: Incorporating Spatial Coherence And Estimating The Number Of Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we address both of these issues. |
Y. Weiss and E. H. Adelson; |
| 1996 | 15 | The Integration Of Optical Flow And Deformable Models With Applications To Human Face Shape And Motion Estimation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a formal methodology for the integration of optical flow and deformable models. |
D. DeCarlo and D. Metaxas; |
| 1993 | 1 | Space-time Gestures IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method for learning, tracking, and recognizing human gestures using a view-based approach to model articulated objects is presented. |
T. Darrell and A. Pentland; |
| 1993 | 2 | Normalized And Differential Convolution IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Three new methods are represented: normalized convolution, differential convolution and normalized differential convolution. |
H. Knutsson and C. -. Westin; |
| 1993 | 3 | Recovering 3D Shape And Motion From Image Streams Using Nonlinear Least Squares IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A shape and motion estimation algorithm based on nonlinear least squares applied to the tracks of features through time is presented. |
R. Szeliski and S. B. Kang; |
| 1993 | 4 | Layered Representation For Motion Analysis IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Standard approaches to motion analysis assume that the optic flow is smooth; such techniques have trouble dealing with occlusion boundaries. |
J. Y. A. Wang and E. H. Adelson; |
| 1993 | 5 | Inferring Global Perceptual Contours From Local Features IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: An attempt is made to solve the problem of imperfect data produced by state-of-the-art edge detectors through the implementation of laws of perceptual grouping, derived from … |
G. Guy and G. Medioni; |
| 1993 | 6 | Automatic Finding Of Main Roads In Aerial Images By Using Geometric-stochastic Models And Estimation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An automated approach to finding main roads in aerial images is presented. |
M. Barzohar and D. B. Cooper; |
| 1993 | 7 | Mixture Models For Optical Flow Computation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new approach for dealing with these issues is presented. |
A. Jepson and M. J. Black; |
| 1993 | 8 | A Multi-resolution Technique For Comparing Images Using The Hausdorff Distance IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An efficient method of computing this distance is developed, based on a multi-resolution tessellation of the space is possible transformations of the model set. |
D. P. Huttenlocher and W. J. Rucklidge; |
| 1993 | 9 | Depth From Focusing And Defocusing IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A model of the blurring effect that takes geometric blurring as well as imaging blurring into consideration in the calibration of the blurring model is proposed. |
Y. Xiong and S. A. Shafer; |
| 1993 | 10 | Parts Of Visual Form: Computational Aspects IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A proposed general principle of form from function motivates a particular partitioning scheme involving two types of parts, neck-based and limb-based. Neck-based parts arise from … |
K. Siddiqi and B. B. Kimia; |
| 1993 | 11 | Temporal-color Space Analysis Of Reflection IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method to analyze a sequence of color images is proposed. |
Y. Sato and K. Ikeuchi; |
| 1993 | 12 | Detecting Activities IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method of activity detection is described. |
R. Polana and R. Nelson; |
| 1993 | 13 | FLASH: A Fast Look-up Algorithm For String Homology IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The algorithm is shown to scale well to databases containing billions of nucleotides with performances that are orders of magnitude better than the fastest of the current techniques. |
A. Califano and I. Rigoutsos; |
| 1993 | 14 | Incremental Recognition Of Pedestrians From Image Sequences IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An approach that uses a volume model consisting of cylinders for model-based recognition of pedestrians in real-world images is presented. |
K. Rohr; |
| 1993 | 15 | Modeling Surfaces Of Arbitrary Topology With Dynamic Particles IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new approach to surface modeling and reconstruction is developed which overcomes some important limitations of existing surface representations methods. |
R. Szeliski; D. Tonnesen and D. Terzopoulos; |
| 1992 | 1 | Performance Of Optical Flow Techniques IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The most accurate methods are found to be the local differential approaches, where nu is computed explicitly in terms of a locally constant or linear model. |
J. L. Barron; D. J. Fleet; S. S. Beauchemin and T. A. Burkitt; |
| 1992 | 2 | Recognizing Human Action In Time-sequential Images Using Hidden Markov Model IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A human action recognition method based on a hidden Markov model (HMM) is proposed. |
J. Yamato; J. Ohya and K. Ishii; |
| 1992 | 3 | Stereo From Uncalibrated Cameras IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The problem of computing placement of points in 3-D space, given two uncalibrated perspective views, is considered. The main theorem shows that the placement of the points is … |
R. Hartley; R. Gupta and T. Chang; |
| 1992 | 4 | A Feature Based Approach To Face Recognition IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A feature-based approach to face recognition in which the features are derived from the intensity data without assuming any knowledge of the face structure is presented. The … |
B. S. Manjunath; R. Chellappa and C. von der Malsburg; |
| 1992 | 5 | Face Recognition Based On Depth And Curvature Features IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Face recognition from a representation based on features extracted from range images is explored. Depth and curvature features have several advantages over more traditional … |
G. G. Gordon; |
| 1992 | 6 | Voronoi Skeletons: Theory And Applications IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel method of robust skeletonization based on the Voronoi diagram of boundary points, which is characterized by correct Euclidean metries and inherent preservation of connectivity, is presented. |
R. Ogniewicz and M. Ilg; |
| 1992 | 7 | Geometric Primitive Extraction Using A Genetic Algorithm IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A genetic algorithm based on a minimal subset representation of a geometric primitive is used to perform primitive extraction. |
G. Roth and M. D. Levine; |
| 1992 | 8 | A Simple Algorithm For Shape From Shading IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A shape-from-shading algorithm that recovers depth from a brightness image typically in fewer than ten iterations, is described. This algorithm, which is a simplification of the … |
M. Bichsel and A. P. Pentland; |
| 1992 | 9 | A Bayesian Treatment Of The Stereo Correspondence Problem Using Half-occluded Regions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An algorithm that incorporates them from the start as a strong clue to depth discontinuities is presented. |
P. N. Belhumeur and D. Mumford; |
| 1992 | 10 | Classification Trees With Neural Network Feature Extraction IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This approach exploits the power of tree classifiers to use appropriate local features at the different levels and nodes of the tree. |
H. Guo and S. B. Gelfand; |
| 1992 | 11 | Extracting The Shape And Roughness Of Specular Lobe Objects Using Four Light Photometric Stereo IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A noncontact method of measuring surface shape and surface roughness for part inspection is proposed. |
F. Solomon and K. Ikeuchi; |
| 1992 | 12 | Hierarchical Decomposition And Axial Shape Description IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular, a method for producing a segmented axial description of a given shape together with a hierarchical decomposition of the shape into its parts is suggested. |
H. Rom and G. Medioni; |
| 1992 | 13 | Recovery Of Temporal Information From Static Images Of Handwriting IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It is suggested that this task requires breaking away from traditional thresholding and thinning techniques, and a framework for such analysis is presented. |
D. S. Doermann and A. Rosenfeld; |
| 1992 | 14 | Shape From Focus System IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A shape-from-focus method that uses different focus levels to obtain a sequence of object images is described. |
S. K. Nayar; |
| 1992 | 15 | Fast Recognition Using Adaptive Subdivisions Of Transformation Space IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An algorithm, RAST, for solving the bounded error recognition problem efficiently using adaptive subdivisions of transformation space, is presented. |
T. M. Breuel; |
| 1991 | 1 | Face Recognition Using Eigenfaces IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An approach to the detection and identification of human faces is presented, and a working, near-real-time face recognition system which tracks a subject’s head and then recognizes the person by comparing characteristics of the face to those of known individuals is described. |
M. A. Turk and A. P. Pentland; |
| 1991 | 2 | A Multiple-baseline Stereo IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A stereo matching method is presented which uses multiple stereo pairs with various baselines to obtain precise depth estimates without suffering from ambiguity. |
M. Okutomi and T. Kanade; |
| 1991 | 3 | Estimation Of Illuminant Direction, Albedo, And Shape From Shading IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A robust approach to recovery of shape from shading information is presented. |
Q. Zheng and R. Chellappa; |
| 1991 | 4 | Recovery Of Non-rigid Motion And Structure IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The elastic properties of real materials provide constraint on the types of non-rigid motion that can occur, and thus allow overconstrained estimates of 3-D non-rigid motion from … |
B. Horowitz and A. Pentland; |
| 1991 | 5 | Probability Distributions Of Optical Flow IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Gradient methods are widely used in the computation of optical flow. |
E. P. Simoncelli; E. H. Adelson and D. J. Heeger; |
| 1991 | 6 | Deformable Kernels For Early Vision IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A technique is presented that allows (1) computing the best approximation of a given family using linear combinations of a small number of basis functions; and (2) describing all finite-dimensional families, i.e. the families of filters for which a finite-dimensional representation is possible with no error. |
P. Perona; |
| 1991 | 7 | Analysis And Solutions Of The Three Point Perspective Pose Estimation Problem IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The major direct solutions to the three-point perspective pose estimation problems are reviewed from a unified perspective. |
R. M. Haralick; D. Lee; K. Ottenburg and M. Nolle; |
| 1991 | 8 | Closed-form Solutions For Physically-based Shape Modeling And Recognition IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An efficient, physically based solution for recovering a 3-D solid model from collections of 3-D surface measurements is presented. |
S. Sclaroff and A. Pentland; |
| 1991 | 9 | Robust Dynamic Motion Estimation Over Time IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel approach to incrementally estimating visual motion over a sequence of images is presented. |
M. J. Black and P. Anandan; |
| 1991 | 10 | A Screw Motion Approach To Uniqueness Analysis Of Head-eye Geometry IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The screw motion theory is used to solve a class of pose determination problems that can be characterized by a homogeneous transform equation of the form AX=XB, where A and B are known motions and X is an unknown coordinate transformation. |
H. H. Chen; |
| 1991 | 11 | Sampling And Reconstruction With Adaptive Meshes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An approach to visual sampling and reconstruction motivated by concepts from numerical grid generation is presented. |
D. Terzopoulos and M. Vasilescu; |
| 1991 | 12 | Topological Segmentation Of Discrete Surfaces IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An approach to the segmentation of a discrete 3-D object into a structure of characteristic topological primitives with attached qualitative features is proposed. |
G. Malandain; N. Ayache and G. Bertrand; |
| 1991 | 13 | Shape Representation And Image Segmentation Using Deformable Surfaces IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A technique for constructing shape representation from images using free-form deformable surfaces is presented. |
H. Delingette; M. Hebert and K. Ikeuchi; |
| 1991 | 14 | The Direct Computation Of Height From Shading IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method for recovering shape from shading that solves directly for the surface height is presented. |
Y. G. Leclerc and A. F. Bobick; |
| 1991 | 15 | Multidimensional Indexing For Recognizing Visual Shapes IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A homogeneous approach for acquisition, storage, and recognition of nonparametric shapes from images, using a novel shape representation based on shape autocorrelation operators is presented. |
A. Califano and R. Mohan; |
| 1989 | 1 | Feature Extraction From Faces Using Deformable Templates IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method for detecting and describing the features of faces using deformable templates is described. |
A. L. Yuille; D. S. Cohen and P. W. Hallinan; |
| 1989 | 2 | Adaptive Smoothing: A General Tool For Early Vision IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors present a method to smooth a signal-whether it is an intensity image, a range image, or a contour-which preserves discontinuities and thus facilitates their detection. |
P. Saint-Marc; J. S. Chen and G. Medioni; |
| 1989 | 3 | An Analytic Solution For The Perspective 4-point Problem IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors propose an analytic solution for the perspective 4-point problem. |
R. Horaud; B. Conio; O. Leboulleux and B. Lacolle; |
| 1989 | 4 | Optimal Motion And Structure Estimation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors present approaches to estimating errors in the optimal solutions, investigate the theoretical lower bounds on the errors in the solutions and compare them with actual errors, and analyze two types of algorithms of optimization: batch and sequential. |
J. Weng; N. Ahuja and T. S. Huang; |
| 1989 | 5 | Computing Oriented Texture Fields IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel algorithm for computing the orientation field for a flowlike texture is presented. |
A. R. Rao and B. G. Schunck; |
| 1989 | 6 | On Reliable Curvature Estimation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An empirical study of the accuracy of five different curvature estimation techniques, using synthetic range images and images obtained from three range sensors, is presented. |
P. J. Flynn and A. K. Jain; |
| 1989 | 7 | Fast Surface Interpolation Using Hierarchical Basis Functions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the present paper, an alternative to multigrid relaxation which is much easier to implement is presented. |
R. Szeliski; |
| 1989 | 8 | 3D Edge Detection Using Recursive Filtering: Application To Scanner Images IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel algorithm for three-dimensional edge detection is proposed. |
O. Monga and R. Deriche; |
| 1989 | 9 | A Markov Random Field Model-based Approach To Image Interpretation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated as a region-based scheme. |
J. W. Modestino and J. Zhang; |
| 1989 | 10 | A Cost Minimization Approach To Edge Detection Using Simulated Annealing IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Edge detection is analyzed as a problem in cost minimization. A cost function is formulated that evaluates the quality of edge configurations. A mathematical description of edges … |
H. L. Tan; S. B. Gelfand and E. J. Delp; |
| 1989 | 11 | Using Polarization To Separate Reflection Components IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A technique is presented which utilizes the polarization properties of reflected light to separate specular and diffuse components of reflection. |
L. B. Wolff; |
| 1989 | 12 | A Simple, Real-time Range Camera IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A simple imaging range sensor is described, based on the measurement of focal error, as described by A. Pentland (1982 and 1987). The current implementation can produce range over … |
A. Pentland; T. Darrell; M. Turk and W. Huang; |
| 1989 | 13 | Parametrically Deformable Contour Models IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Segmentation using boundary finding is enhanced both by considering the boundary as a whole and by using model-based shape information. Flexible constraints, in the form of a … |
L. H. Staib and J. S. Duncan; |
| 1989 | 14 | Locating Human Faces In Newspaper Photographs IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A computational approach to locating human faces in newspaper photographs is described. |
V. Govindaraju; D. B. Sher; R. K. Srihari and S. N. Srihari; |
| 1989 | 15 | Robust Edge Detection IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A robust edge-detection algorithm which performs equally under a wide variety of noisy situations and a broad range of edges is described. |
A. Kundu; |
| 1988 | 1 | On Image Analysis By The Methods Of Moments IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Various types of moments have been used to recognize image patterns in a number of applications. The authors evaluate a number of moments and addresses some fundamental questions, … |
C. -. Teh and R. T. Chin; |
| 1988 | 2 | Integrating Region Growing And Edge Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors present a method that combines region growing and edge detection for image segmentation. |
T. Pavlidis and Y. -. Liow; |
| 1988 | 3 | Image Sequence Enhancement Using Sub-pixel Displacements IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Given a sequence of images taken from a moving camera, they are registered with subpixel accuracy in respect to translation and rotation. The subpixel registration allows image … |
D. Keren; S. Peleg and R. Brada; |
| 1988 | 4 | Object Recognition By Affine Invariant Matching IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Novel techniques are described for model-based recognition of 3-D objects from unknown viewpoints using single-gray-scale images. |
Y. Lamdan; J. T. Schwartz and H. J. Wolfson; |
| 1988 | 5 | Cooperative Methods For Road Tracking In Aerial Imagery IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors discuss a system for road tracking, ARF (A Road Follower), that uses multiple cooperative methods for extracting information about road location and structure from complex aerial imagery. |
D. M. McKeown and J. L. Denlinger; |
| 1988 | 6 | Texture Segmentation Using Voronoi Polygons IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors have developed a texture-segmentation algorithm based on the Voronoi tessellation. |
M. Tuceryan; A. K. Jain and Y. Lee; |
| 1988 | 7 | Recognition Of Handwritten Word: First And Second Order Hidden Markov Model Based Approach IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Once the model is established, the Viterbi algorithm is used to recognize the sequence of letters consisting the word. |
A. Kundu; Y. He and P. Bahl; |
| 1988 | 8 | Projective Invariants Of Shapes IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: He suggests extensions and adaptations of these methods to the needs of machine vision. |
I. Weiss; |
| 1988 | 9 | Estimating Motion/structure From Line Correspondences: A Robust Linear Algorithm And Uniqueness Theorems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A closed-form solution to motion and structure from line correspondences in monocular perspective image sequences is presented. |
Juyang Weng; Yuncai Liu; T. S. Huang and N. Ahuja; |
| 1988 | 10 | Generalizing Epipolar-plane Image Analysis On The Spatiotemporal Surface IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The previous implementations of the authors’ epipolar-plane image-analysis mapping technique demonstrated the feasibility and benefits of the approach, but were carried out for … |
H. H. Baker and R. C. Bolles; |
| 1988 | 11 | Pyramid Based Depth From Focus IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method is presented for depth recovery through the analysis of scene sharpness across changing focus position. |
T. Darrell and K. Wohn; |
| 1988 | 12 | Depth Recovery From Blurred Edges IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method is proposed for recovering depth from a measure of the degree of blur of an edge. |
M. Subbarao and N. Gurumoorthy; |
| 1988 | 13 | Computing The Aspect Graph For Line Drawings Of Polyhedral Objects IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The authors present an algorithm for computing the viewing data of polyhedral objects. |
Z. Gigus and J. Malik; |
| 1988 | 14 | Determination Of Camera Location From 2D To 3D Line And Point Correspondences IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A novel method for the determination of camera location from 2-D to 3-D line or point correspondences is presented. |
Y. Liu; T. S. Huang and O. D. Faugeras; |
| 1988 | 15 | Evaluation Of Quantization Error In Computer Vision IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The authors develop the mathematical tools for the computation of the average error due to quantization. They can be used in estimating the actual error occurring in the … |
B. R. Kamgar-Parsi and B. Z. Kamgar-Parsi; |