Most Influential ICCV Papers (2026-03 Version)
The International Conference on Computer Vision (ICCV) is one of the top computer vision conferences in the world. Paper Digest Team analyzes all papers published on ICCV 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: 2026-03)
To search or review papers within ICCV related to a specific topic, please use the search by venue (ICCV) and review by venue (ICCV) services. To browse the most productive ICCV authors by year ranked by #papers accepted, here are the most productive ICCV authors grouped by year.
Since 2018, Paper Digest has built a foundation of data spanning decades of conferences, journals, and research topics. The platform features a daily digest service that sifts through tens of thousands of new papers, clinical trials, news articles, and community posts, filtering the noise to highlight what matters most to specific interests. Beyond daily updates, dozens of built-in research tools streamline the academic workflow, supporting efficient reading and writing, comprehensive literature reviews, and automated research report generation.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Most Influential ICCV Papers (2026-03 Version)
| Year | Rank | Paper | Author(s) |
|---|---|---|---|
| 2025 | 1 | LLaVA-CoT: Let Vision Language Models Reason Step-by-Step IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we introduce LLaVA-CoT, a large VLM designed to conduct autonomous multistage reasoning. |
GUOWEI XU et. al. |
| 2025 | 2 | Visual-RFT: Visual Reinforcement Fine-Tuning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce.Recent open-source work like DeepSeek-R1 demonstrates that reinforcement learning with verifiable reward is possibly one key direction in reproducing o1.While the R1-style model has demonstrated success in language models, its application in multi-modal domains remains under-explored. |
ZIYU LIU et. al. |
| 2025 | 3 | R1-Onevision: Advancing Generalized Multimodal Reasoning Through Cross-Modal Formalization IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we introduce R1-Onevision, a multimodal reasoning model designed to bridge the gap between visual perception and deep reasoning. |
YI YANG et. al. |
| 2025 | 4 | LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In response, we propose PruMerge, a novel adaptive visual token reduction strategy that significantly reduces the number of visual tokens without compromising the performance of LMMs. |
Yuzhang Shang; Mu Cai; Bingxin Xu; Yong Jae Lee; Yan Yan; |
| 2025 | 5 | LVBench: An Extreme Long Video Understanding Benchmark IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: However, these advancements fall short of meeting the demands of real-world applications such as embodied intelligence for long-term decision-making, in-depth movie reviews and discussions, and live sports commentary, all of which require comprehension of long videos spanning several hours. To address this gap, we introduce LVBench, a benchmark specifically designed for long video understanding. |
WEIHAN WANG et. al. |
| 2025 | 6 | OminiControl: Minimal and Universal Control for Diffusion Transformer IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present OminiControl, a novel approach that rethinks how image conditions are integrated into Diffusion Transformer (DiT) architectures. |
Zhenxiong Tan; Songhua Liu; Xingyi Yang; Qiaochu Xue; Xinchao Wang; |
| 2025 | 7 | CoTracker3: Simpler and Better Point Tracking By Pseudo-Labelling Real Videos IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce CoTracker3, a new state-of-the-art point tracker. |
NIKITA KARAEV et. al. |
| 2025 | 8 | R1-VL: Learning to Reason with Multimodal Large Language Models Via Step-wise Group Relative Policy Optimization IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Recent studies generally enhance MLLMs’ reasoning capabilities via supervised fine-tuning on high-quality chain-of-thought reasoning data, which often leads models to merely imitate successful reasoning paths without understanding what the wrong reasoning paths are.In this work, we aim to enhance the MLLMs’ reasoning ability beyond passively imitating positive reasoning paths. |
JINGYI ZHANG et. al. |
| 2025 | 9 | Shape of Motion: 4D Reconstruction from A Single Video IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce a method for reconstructing generic dynamic scenes, featuring explicit, persistent 3D motion trajectories in the world coordinate frame, from casually captured monocular videos. |
QIANQIAN WANG et. al. |
| 2025 | 10 | VACE: All-in-One Video Creation and Editing IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce VACE, which enables users to perform Video tasks within an All-in-one framework for Creation and Editing. |
ZEYINZI JIANG et. al. |
| 2025 | 11 | MetaMorph: Multimodal Understanding and Generation Via Instruction Tuning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we propose Visual-Predictive Instruction Tuning (VPiT) – a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph into an unified autoregressive model capable of generating both text and visual tokens. |
SHENGBANG TONG et. al. |
| 2025 | 12 | ReCamMaster: Camera-Controlled Generative Rendering from A Single Video IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: It is non-trivial due to the extra constraints of maintaining multiple-frame appearance and dynamic synchronization. To address this, we present ReCamMaster, a camera-controlled generative video re-rendering framework that reproduces the dynamic scene of an input video at novel camera trajectories. |
JIANHONG BAI et. al. |
| 2025 | 13 | FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Here, we introduce FlowEdit, a text-based editing method for pre-trained T2I flow models, which is inversion-free, optimization-free and model agnostic. |
Vladimir Kulikov; Matan Kleiner; Inbar Huberman-Spiegelglas; Tomer Michaeli; |
| 2025 | 14 | OmniHuman-1: Rethinking The Scaling-Up of One-Stage Conditioned Human Animation Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose OmniHuman, a Diffusion Transformer-based framework that scales up data by mixing motion-related conditions into the training phase. |
GAOJIE LIN et. al. |
| 2025 | 15 | Randomized Autoregressive Visual Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. |
Qihang Yu; Ju He; Xueqing Deng; Xiaohui Shen; Liang-Chieh Chen; |
| 2023 | 1 | Segment Anything IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. |
ALEXANDER KIRILLOV et. al. |
| 2023 | 2 | Adding Conditional Control to Text-to-Image Diffusion Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. |
Lvmin Zhang; Anyi Rao; Maneesh Agrawala; |
| 2023 | 3 | Scalable Diffusion Models with Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. |
William Peebles; Saining Xie; |
| 2023 | 4 | Sigmoid Loss for Language Image Pre-Training IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a simple pairwise sigmoid loss for image-text pre-training. |
Xiaohua Zhai; Basil Mustafa; Alexander Kolesnikov; Lucas Beyer; |
| 2023 | 5 | Zero-1-to-3: Zero-shot One Image to 3D Object IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. |
RUOSHI LIU et. al. |
| 2023 | 6 | Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we propose a new T2V generation setting–One-Shot Video Tuning, where only one text-video pair is presented. |
JAY ZHANGJIE WU et. al. |
| 2023 | 7 | LightGlue: Local Feature Matching at Light Speed IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce LightGlue, a deep neural network that learns to match local features across images. |
Philipp Lindenberger; Paul-Edouard Sarlin; Marc Pollefeys; |
| 2023 | 8 | Text2Video-Zero: Text-to-Image Diffusion Models Are Zero-Shot Video Generators IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task, zero-shot text-to-video generation, and propose a low-cost approach (without any training or optimization) by leveraging the power of existing text-to-image synthesis methods (e.g., Stable Diffusion), making them suitable for the video domain. |
LEVON KHACHATRYAN et. al. |
| 2023 | 9 | Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we propose a new method of Fantasia3D for high-quality text-to-3D content creation. |
Rui Chen; Yongwei Chen; Ningxin Jiao; Kui Jia; |
| 2023 | 10 | Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We show how ideas from rendering and signal processing can be used to construct a technique that combines mip-NeRF 360 and grid-based models such as Instant NGP to yield error rates that are 8%-77% lower than either prior technique, and that trains 24x faster than mip-NeRF 360. |
Jonathan T. Barron; Ben Mildenhall; Dor Verbin; Pratul P. Srinivasan; Peter Hedman; |
| 2023 | 11 | MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we develop MasaCtrl, a tuning-free method to achieve consistent image generation and complex non-rigid image editing simultaneously. |
MINGDENG CAO et. al. |
| 2023 | 12 | Structure and Content-Guided Video Synthesis with Diffusion Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we present a structure and content-guided video diffusion model that edits videos based on descriptions of the desired output. |
Patrick Esser; Johnathan Chiu; Parmida Atighehchian; Jonathan Granskog; Anastasis Germanidis; |
| 2023 | 13 | DiffusionDet: Diffusion Model for Object Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. |
Shoufa Chen; Peize Sun; Yibing Song; Ping Luo; |
| 2023 | 14 | LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we propose a novel method, LLM-Planner, that harnesses the power of large language models to do few-shot planning for embodied agents. |
CHAN HEE SONG et. al. |
| 2023 | 15 | LERF: Language Embedded Radiance Fields IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Humans describe the physical world using natural language to refer to specific 3D locations based on a vast range of properties: visual appearance, semantics, abstract associations, or actionable affordances. In this work we propose Language Embedded Radiance Fields (LERFs), a method for grounding language embeddings from off-the-shelf models like CLIP into NeRF, which enable these types of open-ended language queries in 3D. |
Justin Kerr; Chung Min Kim; Ken Goldberg; Angjoo Kanazawa; Matthew Tancik; |
| 2021 | 1 | Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. |
ZE LIU et. al. |
| 2021 | 2 | Emerging Properties in Self-Supervised Vision Transformers IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). |
MATHILDE CARON et. al. |
| 2021 | 3 | Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Unlike the recently-proposed Vision Transformer (ViT) that was designed for image classification specifically, we introduce the Pyramid Vision Transformer (PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks. |
WENHAI WANG et. al. |
| 2021 | 4 | ViViT: A Video Vision Transformer IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. |
ANURAG ARNAB et. al. |
| 2021 | 5 | Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our solution, which we call mip-NeRF (a la mipmap), extends NeRF to represent the scene at a continuously-valued scale. |
JONATHAN T. BARRON et. al. |
| 2021 | 6 | Vision Transformers for Dense Prediction IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce dense prediction transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. |
Rene Ranftl; Alexey Bochkovskiy; Vladlen Koltun; |
| 2021 | 7 | Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-ViT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study. |
LI YUAN et. al. |
| 2021 | 8 | CvT: Introducing Convolutions to Vision Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. |
HAIPING WU et. al. |
| 2021 | 9 | An Empirical Study of Training Self-Supervised Vision Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT. |
Xinlei Chen; Saining Xie; Kaiming He; |
| 2021 | 10 | The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We find that using larger models and artificial data augmentations can improve robustness on real-world distribution shifts, contrary to claims in prior work. |
DAN HENDRYCKS et. al. |
| 2021 | 11 | CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. |
Chun-Fu (Richard) Chen; Quanfu Fan; Rameswar Panda; |
| 2021 | 12 | Segmenter: Transformer for Semantic Segmentation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we introduce Segmenter, a transformer model for semantic segmentation. |
Robin Strudel; Ricardo Garcia; Ivan Laptev; Cordelia Schmid; |
| 2021 | 13 | Multiscale Vision Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. |
HAOQI FAN et. al. |
| 2021 | 14 | Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our objective in this work is video-text retrieval – in particular a joint embedding that enables efficient text-to-video retrieval. |
Max Bain; Arsha Nagrani; Gul Varol; Andrew Zisserman; |
| 2021 | 15 | StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, weexplore leveraging the power of recently introduced Con-trastive Language-Image Pre-training (CLIP) models in or-der to develop a text-based interface for StyleGAN imagemanipulation that does not require such manual effort. |
Or Patashnik; Zongze Wu; Eli Shechtman; Daniel Cohen-Or; Dani Lischinski; |
| 2019 | 1 | Searching for MobileNetV3 IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. |
ANDREW HOWARD et. al. |
| 2019 | 2 | FCOS: Fully Convolutional One-Stage Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. |
Zhi Tian; Chunhua Shen; Hao Chen; Tong He; |
| 2019 | 3 | CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We therefore propose the CutMix augmentation strategy: patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches. |
SANGDOO YUN et. al. |
| 2019 | 4 | SlowFast Networks for Video Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present SlowFast networks for video recognition. |
Christoph Feichtenhofer; Haoqi Fan; Jitendra Malik; Kaiming He; |
| 2019 | 5 | CenterNet: Keypoint Triplets for Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents an efficient solution that explores the visual patterns within individual cropped regions with minimal costs. |
KAIWEN DUAN et. al. |
| 2019 | 6 | KPConv: Flexible and Deformable Convolution for Point Clouds IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. |
HUGUES THOMAS et. al. |
| 2019 | 7 | CCNet: Criss-Cross Attention for Semantic Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we propose a Criss-Cross Network (CCNet) for obtaining such contextual information in a more effective and efficient way. |
ZILONG HUANG et. al. |
| 2019 | 8 | FaceForensics++: Learning to Detect Manipulated Facial Images IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. |
ANDREAS ROSSLER et. al. |
| 2019 | 9 | Digging Into Self-Supervised Monocular Depth Estimation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. |
Clement Godard; Oisin Mac Aodha; Michael Firman; Gabriel J. Brostow; |
| 2019 | 10 | SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we introduce a large dataset to propel research on laser-based semantic segmentation. |
JENS BEHLEY et. al. |
| 2019 | 11 | Moment Matching for Multi-Source Domain Adaptation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning approach, Moment Matching for Multi-Source Domain Adaptation (M3SDA), which aims to transfer knowledge learned from multiple labeled source domains to an unlabeled target domain by dynamically aligning moments of their feature distributions. |
XINGCHAO PENG et. al. |
| 2019 | 12 | YOLACT: Real-Time Instance Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a simple, fully-convolutional model for real-time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan Xp, which is significantly faster than any previous competitive approach. |
Daniel Bolya; Chong Zhou; Fanyi Xiao; Yong Jae Lee; |
| 2019 | 13 | TSM: Temporal Shift Module for Efficient Video Understanding IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. |
Ji Lin; Chuang Gan; Song Han; |
| 2019 | 14 | Free-Form Image Inpainting With Gated Convolution IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a generative image inpainting system to complete images with free-form mask and guidance. |
JIAHUI YU et. al. |
| 2019 | 15 | Habitat: A Platform for Embodied AI Research IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present Habitat, a platform for research in embodied artificial intelligence (AI). |
MANOLIS SAVVA et. al. |
| 2017 | 1 | Mask R-CNN IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a conceptually simple, flexible, and general framework for object instance segmentation. |
Kaiming He; Georgia Gkioxari; Piotr Dollar; Ross Girshick; |
| 2017 | 2 | Focal Loss For Dense Object Detection IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we investigate why this is the case. |
Tsung-Yi Lin; Priya Goyal; Ross Girshick; Kaiming He; Piotr Dollar; |
| 2017 | 3 | Grad-CAM: Visual Explanations From Deep Networks Via Gradient-Based Localization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. |
RAMPRASAATH R. SELVARAJU et. al. |
| 2017 | 4 | Deformable Convolutional Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deformable RoI pooling. |
JIFENG DAI et. al. |
| 2017 | 5 | Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. |
Jun-Yan Zhu; Taesung Park; Phillip Isola; Alexei A. Efros; |
| 2017 | 6 | Arbitrary Style Transfer In Real-Time With Adaptive Instance Normalization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. |
Xun Huang; Serge Belongie; |
| 2017 | 7 | Least Squares Generative Adversarial Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. |
XUDONG MAO et. al. |
| 2017 | 8 | StackGAN: Text To Photo-Realistic Image Synthesis With Stacked Generative Adversarial Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) to generate 256×256 photo-realistic images conditioned on text descriptions. |
HAN ZHANG et. al. |
| 2017 | 9 | Channel Pruning For Accelerating Very Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. |
Yihui He; Xiangyu Zhang; Jian Sun; |
| 2017 | 10 | Learning Efficient Convolutional Networks Through Network Slimming IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the model size; 2) decrease the run-time memory footprint; and 3) lower the number of computing operations, without compromising accuracy. |
ZHUANG LIU et. al. |
| 2017 | 11 | Revisiting Unreasonable Effectiveness Of Data In Deep Learning Era IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper takes a step towards clearing the clouds of mystery surrounding the relationship between `enormous data’ and visual deep learning. |
Chen Sun; Abhinav Shrivastava; Saurabh Singh; Abhinav Gupta; |
| 2017 | 12 | DualGAN: Unsupervised Dual Learning For Image-To-Image Translation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Inspired by dual learning from natural language translation, we develop a novel mechanism, which enables image translators to be trained from two sets of images from two domains. |
Zili Yi; Hao Zhang; Ping Tan; Minglun Gong; |
| 2017 | 13 | Unlabeled Samples Generated By GAN Improve The Person Re-Identification Baseline In Vitro IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. |
Zhedong Zheng; Liang Zheng; Yi Yang; |
| 2017 | 14 | AOD-Net: All-In-One Dehazing Network IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). |
Boyi Li; Xiulian Peng; Zhangyang Wang; Jizheng Xu; Dan Feng; |
| 2017 | 15 | ThiNet: A Filter Level Pruning Method For Deep Neural Network Compression IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose an efficient and unified framework, namely ThiNet, to simultaneously accelerate and compress CNN models in both training and inference stages. |
Jian-Hao Luo; Jianxin Wu; Weiyao Lin; |
| 2015 | 1 | Fast R-CNN IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. |
Ross Girshick; |
| 2015 | 2 | Delving Deep Into Rectifiers: Surpassing Human-Level Performance On ImageNet Classification IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we study rectifier neural networks for image classification from two aspects. |
Kaiming He; Xiangyu Zhang; Shaoqing Ren; Jian Sun; |
| 2015 | 3 | Deep Learning Face Attributes In The Wild IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a novel deep learning framework for attribute prediction in the wild. |
Ziwei Liu; Ping Luo; Xiaogang Wang; Xiaoou Tang; |
| 2015 | 4 | Learning Spatiotemporal Features With 3D Convolutional Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. |
Du Tran; Lubomir Bourdev; Rob Fergus; Lorenzo Torresani; Manohar Paluri; |
| 2015 | 5 | VQA: Visual Question Answering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose the task of free-form and open-ended Visual Question Answering (VQA). We provide a dataset containing 0.25M images, 0.76M questions, and 10M answers (www.visualqa.org), and discuss the information it provides. |
STANISLAW ANTOL et. al. |
| 2015 | 6 | FlowNet: Learning Optical Flow With Convolutional Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we construct CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. Since existing ground truth data sets are not sufficiently large to train a CNN, we generate a large synthetic Flying Chairs dataset. |
ALEXEY DOSOVITSKIY et. al. |
| 2015 | 7 | Learning Deconvolution Network For Semantic Segmentation IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. |
Hyeonwoo Noh; Seunghoon Hong; Bohyung Han; |
| 2015 | 8 | Scalable Person Re-Identification: A Benchmark IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. |
LIANG ZHENG et. al. |
| 2015 | 9 | Holistically-Nested Edge Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We develop a new edge detection algorithm that addresses two critical issues in this long-standing vision problem: (1) holistic image training; and (2) multi-scale feature learning. |
Saining Xie; Zhuowen Tu; |
| 2015 | 10 | Multi-View Convolutional Neural Networks For 3D Shape Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We address this question in the context of learning to recognize 3D shapes from a collection of their rendered views on 2D images. |
Hang Su; Subhransu Maji; Evangelos Kalogerakis; Erik Learned-Miller; |
| 2015 | 11 | Unsupervised Visual Representation Learning By Context Prediction IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. |
Carl Doersch; Abhinav Gupta; Alexei A. Efros; |
| 2015 | 12 | Predicting Depth, Surface Normals And Semantic Labels With A Common Multi-Scale Convolutional Architecture IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. |
David Eigen; Rob Fergus; |
| 2015 | 13 | Aligning Books And Movies: Towards Story-Like Visual Explanations By Watching Movies And Reading Books IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To align movies and books we propose a neural sentence embedding that is trained in an unsupervised way from a large corpus of books, as well as a video-text neural embedding for computing similarities between movie clips and sentences in the book. |
YUKUN ZHU et. al. |
| 2015 | 14 | Conditional Random Fields As Recurrent Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. |
SHUAI ZHENG et. al. |
| 2015 | 15 | Flickr30k Entities: Collecting Region-to-Phrase Correspondences For Richer Image-to-Sentence Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity. |
BRYAN A. PLUMMER et. al. |
| 2013 | 1 | Action Recognition With Improved Trajectories IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper improves their performance by taking into account camera motion to correct them. |
Heng Wang; Cordelia Schmid; |
| 2013 | 2 | Transfer Feature Learning With Joint Distribution Adaptation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we put forward a novel transfer learning approach, referred to as Joint Distribution Adaptation (JDA). |
Mingsheng Long; Jianmin Wang; Guiguang Ding; Jiaguang Sun; Philip S. Yu; |
| 2013 | 3 | DeepFlow: Large Displacement Optical Flow With Deep Matching IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a descriptor matching algorithm, tailored to the optical flow problem, that allows to boost performance on fast motions. |
Philippe Weinzaepfel; Jerome Revaud; Zaid Harchaoui; Cordelia Schmid; |
| 2013 | 4 | Unsupervised Visual Domain Adaptation Using Subspace Alignment IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we introduce a new domain adaptation (DA) algorithm where the source and target domains are represented by subspaces described by eigenvectors. |
Basura Fernando; Amaury Habrard; Marc Sebban; Tinne Tuytelaars; |
| 2013 | 5 | Anchored Neighborhood Regression For Fast Example-Based Super-Resolution IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes fast super-resolution methods while making no compromise on quality. |
Radu Timofte; Vincent De Smet; Luc Van Gool; |
| 2013 | 6 | Abnormal Event Detection At 150 FPS In MATLAB IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Based on inherent redundancy of video structures, we propose an efficient sparse combination learning framework. |
Cewu Lu; Jianping Shi; Jiaya Jia; |
| 2013 | 7 | Efficient Image Dehazing With Boundary Constraint And Contextual Regularization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose an efficient regularization method to remove hazes from a single input image. |
Gaofeng Meng; Ying Wang; Jiangyong Duan; Shiming Xiang; Chunhong Pan; |
| 2013 | 8 | Structured Forests For Fast Edge Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector. |
Piotr Dollar; C. L. Zitnick; |
| 2013 | 9 | Towards Understanding Action Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We evaluate current methods using this dataset and systematically replace the output of various algorithms with ground truth. |
Hueihan Jhuang; Juergen Gall; Silvia Zuffi; Cordelia Schmid; Michael J. Black; |
| 2013 | 10 | SUN3D: A Database Of Big Spaces Reconstructed Using SfM And Object Labels IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we introduce SUN3D, a large-scale RGB-D video database with camera pose and object labels, capturing the full 3D extent of many places. |
Jianxiong Xiao; Andrew Owens; Antonio Torralba; |
| 2013 | 11 | Robust Face Landmark Estimation Under Occlusion IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a novel method, called Robust Cascaded Pose Regression (RCPR) which reduces exposure to outliers by detecting occlusions explicitly and using robust shape-indexed features. |
Xavier P. Burgos-Artizzu; Pietro Perona; Piotr Dollar; |
| 2013 | 12 | Saliency Detection Via Dense And Sparse Reconstruction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a visual saliency detection algorithm from the perspective of reconstruction errors. |
Xiaohui Li; Huchuan Lu; Lihe Zhang; Xiang Ruan; Ming-Hsuan Yang; |
| 2013 | 13 | Depth From Combining Defocus And Correspondence Using Light-Field Cameras IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we present a novel simple and principled algorithm that computes dense depth estimation by combining both defocus and correspondence depth cues. |
Michael W. Tao; Sunil Hadap; Jitendra Malik; Ravi Ramamoorthi; |
| 2013 | 14 | Joint Deep Learning For Pedestrian Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation. |
Wanli Ouyang; Xiaogang Wang; |
| 2013 | 15 | Fast Object Segmentation In Unconstrained Video IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a technique for separating foreground objects from the background in a video. |
Anestis Papazoglou; Vittorio Ferrari; |
| 2011 | 1 | ORB: An Efficient Alternative To SIFT Or SURF IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise. |
E. Rublee; V. Rabaud; K. Konolige and G. Bradski; |
| 2011 | 2 | HMDB: A Large Video Database For Human Motion Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To address this issue we collected the largest action video database to-date with 51 action categories, which in total contain around 7,000 manually annotated clips extracted from a variety of sources ranging from digitized movies to YouTube. |
H. Kuehne; H. Jhuang; E. Garrote; T. Poggio and T. Serre; |
| 2011 | 3 | BRISK: Binary Robust Invariant Scalable Keypoints IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we propose BRISK, a novel method for keypoint detection, description and matching. |
S. Leutenegger; M. Chli and R. Y. Siegwart; |
| 2011 | 4 | DTAM: Dense Tracking And Mapping In Real-time IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We use the hundreds of images available in a video stream to improve the quality of a simple photometric data term, and minimise a global spatially regularised energy functional in a novel non-convex optimisation framework. |
R. A. Newcombe; S. J. Lovegrove and A. J. Davison; |
| 2011 | 5 | Sparse Representation Or Collaborative Representation: Which Helps Face Recognition? IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Consequently, we propose a very simple yet much more efficient face classification scheme, namely CR based classification with regularized least square (CRC_RLS). |
L. Zhang; M. Yang and Xiangchu Feng; |
| 2011 | 6 | Semantic Contours From Inverse Detectors IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: For this purpose, we present a simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours. In order to study the problem and evaluate quantitatively our approach, we present a dataset of semantic exterior boundaries on more than 20, 000 object instances belonging to 20 categories, using the images from the VOC2011 PASCAL challenge [7]. |
B. Hariharan; P. Arbel�ez; L. Bourdev; S. Maji and J. Malik; |
| 2011 | 7 | Struck: Structured Output Tracking With Kernels IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. |
S. Hare; A. Saffari and P. H. S. Torr; |
| 2011 | 8 | From Learning Models Of Natural Image Patches To Whole Image Restoration IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work we answer these questions. |
D. Zoran and Y. Weiss; |
| 2011 | 9 | Adaptive Deconvolutional Networks For Mid And High Level Feature Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. |
M. D. Zeiler; G. W. Taylor and R. Fergus; |
| 2011 | 10 | End-to-end Scene Text Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper focuses on the problem of word detection and recognition in natural images. |
Kai Wang; B. Babenko and S. Belongie; |
| 2011 | 11 | Domain Adaptation For Object Recognition: An Unsupervised Approach IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not have correspondences between object categories across domains). |
R. Gopalan; Ruonan Li and R. Chellappa; |
| 2011 | 12 | Relative Attributes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose to model relative attributes. |
D. Parikh and K. Grauman; |
| 2011 | 13 | Fisher Discrimination Dictionary Learning For Sparse Representation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a novel dictionary learning (DL) method to improve the pattern classification performance. |
M. Yang; L. Zhang; X. Feng and D. Zhang; |
| 2011 | 14 | Ensemble Of Exemplar-SVMs For Object Detection And Beyond IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes a conceptually simple but surprisingly powerful method which combines the effectiveness of a discriminative object detector with the explicit correspondence offered by a nearest-neighbor approach. |
T. Malisiewicz; A. Gupta and A. A. Efros; |
| 2011 | 15 | Segmentation As Selective Search For Object Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Therefore, we adapt segmentation as a selective search by reconsidering segmentation: We propose to generate many approximate locations over few and precise object delineations because (1) an object whose location is never generated can not be recognised and (2) appearance and immediate nearby context are most effective for object recognition. |
K. E. A. van de Sande; J. R. R. Uijlings; T. Gevers and A. W. M. Smeulders; |
| 2009 | 1 | Building Rome In A Day IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo sharing sites. |
S. Agarwal; N. Snavely; I. Simon; S. M. Seitz and R. Szeliski; |
| 2009 | 2 | What Is The Best Multi-stage Architecture For Object Recognition? IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper addresses three questions: 1. |
K. Jarrett; K. Kavukcuoglu; M. Ranzato and Y. LeCun; |
| 2009 | 3 | Learning To Predict Where Humans Look IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To address this problem, we collected eye tracking data of 15 viewers on 1003 images and use this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features. |
T. Judd; K. Ehinger; F. Durand and A. Torralba; |
| 2009 | 4 | Super-resolution From A Single Image IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we propose a unified framework for combining these two families of methods. |
D. Glasner; S. Bagon and M. Irani; |
| 2009 | 5 | Tensor Completion For Estimating Missing Values In Visual Data IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we propose an algorithm to estimate missing values in tensors of visual data. |
Ji Liu; P. Musialski; P. Wonka and Jieping Ye; |
| 2009 | 6 | Non-local Sparse Models For Image Restoration IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose in this paper to unify two different approaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has proven to be very effective in image reconstruction and classification tasks. |
J. Mairal; F. Bach; J. Ponce; G. Sapiro and A. Zisserman; |
| 2009 | 7 | You’ll Never Walk Alone: Modeling Social Behavior For Multi-target Tracking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work, we introduce a model of dynamic social behavior, inspired by models developed for crowd simulation. |
S. Pellegrini; A. Ess; K. Schindler and L. van Gool; |
| 2009 | 8 | Attribute And Simile Classifiers For Face Verification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present two novel methods for face verification. For further testing across pose, illumination, and expression, we introduce a new data set – termed PubFig – of real-world images of public figures (celebrities and politicians) acquired from the internet. |
N. Kumar; A. C. Berg; P. N. Belhumeur and S. K. Nayar; |
| 2009 | 9 | Fast Visibility Restoration From A Single Color Or Gray Level Image IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce a novel algorithm and variants for visibility restoration from a single image. |
J. Tarel and N. Hauti�re; |
| 2009 | 10 | Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We address the classic problems of detection, segmentation and pose estimation of people in images with a novel definition of a part, a poselet. To permit this we have built a new dataset, H3D, of annotations of humans in 2D photographs with 3D joint information, inferred using anthropometric constraints. |
L. Bourdev and J. Malik; |
| 2009 | 11 | Fast And Robust Earth Mover’s Distances IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a new algorithm for a robust family of Earth Mover’s Distances – EMDs with thresholded ground distances. |
O. Pele and M. Werman; |
| 2009 | 12 | Kernelized Locality-sensitive Hashing For Scalable Image Search IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Recent work has explored ways to embed high-dimensional features or complex distance functions into a low-dimensional Hamming space where items can be efficiently searched. |
B. Kulis and K. Grauman; |
| 2009 | 13 | Is That You? Metric Learning Approaches For Face Identification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we present two methods for learning robust distance measures: (a) a logistic discriminant approach which learns the metric from a set of labelled image pairs (LDML) and (b) a nearest neighbour approach which computes the probability for two images to belong to the same class (MkNN). |
M. Guillaumin; J. Verbeek and C. Schmid; |
| 2009 | 14 | On Feature Combination For Multiclass Object Classification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we study several models that aim at learning the correct weighting of different features from training data. |
P. Gehler and S. Nowozin; |
| 2009 | 15 | Multiple Kernels For Object Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image sub-windows. |
A. Vedaldi; V. Gulshan; M. Varma and A. Zisserman; |
| 2007 | 1 | A Database And Evaluation Methodology For Optical Flow IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our goal is to establish a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. |
S. Baker; S. Roth; D. Scharstein; M. J. Black; J. P. Lewis and R. Szeliski; |
| 2007 | 2 | Image Classification Using Random Forests And Ferns IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We explore the problem of classifying images by the object categories they contain in the case of a large number of object categories. |
A. Bosch; A. Zisserman and X. Munoz; |
| 2007 | 3 | Probabilistic Linear Discriminant Analysis For Inferences About Identity IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we present a novel algorithm designed for these conditions. |
S. J. D. Prince and J. H. Elder; |
| 2007 | 4 | Total Recall: Automatic Query Expansion With A Generative Feature Model For Object Retrieval IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we bring query expansion into the visual domain via two novel contributions. |
O. Chum; J. Philbin; J. Sivic; M. Isard and A. Zisserman; |
| 2007 | 5 | Multi-View Stereo For Community Photo Collections IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. |
M. Goesele; N. Snavely; B. Curless; H. Hoppe and S. M. Seitz; |
| 2007 | 6 | What, Where And Who? Classifying Events By Scene And Object Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we use a number of sport games such as snow boarding, rock climbing or badminton to demonstrate event classification. We have assembled a highly challenging database of 8 widely varied sport events. |
L. Li and Li Fei-Fei; |
| 2007 | 7 | A Biologically Inspired System For Action Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a biologically-motivated system for the recognition of actions from video sequences. |
H. Jhuang; T. Serre; L. Wolf and T. Poggio; |
| 2007 | 8 | Objects In Context IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work we propose to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model. |
A. Rabinovich; A. Vedaldi; C. Galleguillos; E. Wiewiora and S. Belongie; |
| 2007 | 9 | Depth And Appearance For Mobile Scene Analysis IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we address the challenging problem of simultaneous pedestrian detection and ground-plane estimation from video while walking through a busy pedestrian zone. |
A. Ess; B. Leibe and L. Van Gool; |
| 2007 | 10 | Semi-supervised Discriminant Analysis IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a novel method, called Semi- supervised Discriminant Analysis (SDA), which makes use of both labeled and unlabeled samples. |
D. Cai; X. He and J. Han; |
| 2007 | 11 | Eyeblink-based Anti-Spoofing In Face Recognition From A Generic Webcamera IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a real-time liveness detection approach against photograph spoofing in face recognition, by recognizing spontaneous eyeblinks, which is a non-intrusive manner. |
G. Pan; L. Sun; Z. Wu and S. Lao; |
| 2007 | 12 | Learning The Discriminative Power-Invariance Trade-Off IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our focus, in this paper, is on learning the optimal tradeoff for classification given a particular training set and prior constraints. |
M. Varma and D. Ray; |
| 2007 | 13 | A Geodesic Framework For Fast Interactive Image And Video Segmentation And Matting IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: An interactive framework for soft segmentation and matting of natural images and videos is presented in this paper. |
X. Bai and G. Sapiro; |
| 2007 | 14 | Non-homogeneous Content-driven Video-retargeting IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: An efficient algorithm for video retargeting is introduced. |
L. Wolf; M. Guttmann and D. Cohen-Or; |
| 2007 | 15 | Learning 3-D Scene Structure From A Single Still Image IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our goal is to create 3D models which are both quantitatively accurate as well as visually pleasing. |
A. Saxena; M. Sun and A. Y. Ng; |
| 2005 | 1 | Actions As Space-time Shapes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We adopt a recent approach by Gorelick et al. (2004) for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. |
M. Blank; L. Gorelick; E. Shechtman; M. Irani and R. Basri; |
| 2005 | 2 | The Pyramid Match Kernel: Discriminative Classification With Sets Of Image Features IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a new fast kernel function which maps unordered feature sets to multi-resolution histograms and computes a weighted histogram intersection in this space. |
K. Grauman and T. Darrell; |
| 2005 | 3 | Neighborhood Preserving Embedding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we propose a novel subspace learning algorithm called neighborhood preserving embedding (NPE). |
Xiaofei He; Deng Cai; Shuicheng Yan and Hong-Jiang Zhang; |
| 2005 | 4 | A Spectral Technique For Correspondence Problems Using Pairwise Constraints IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present an efficient spectral method for finding consistent correspondences between two sets of features. |
M. Leordeanu and M. Hebert; |
| 2005 | 5 | Fusing Points And Lines For High Performance Tracking IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In particular, we present a method for integrating the two systems and robustly combining the pose estimates they produce. |
E. Rosten and T. Drummond; |
| 2005 | 6 | Discovering Objects And Their Location In Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Here we treat object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics. |
J. Sivic; B. C. Russell; A. A. Efros; A. Zisserman and W. T. Freeman; |
| 2005 | 7 | Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-statistical Model For Face Representation And Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes a novel non-statistics based face representation approach, local Gabor binary pattern histogram sequence (LGBPHS), in which training procedure is unnecessary to construct the face model, so that the generalizability problem is naturally avoided. |
Wenchao Zhang; Shiguang Shan; Wen Gao; Xilin Chen and Hongming Zhang; |
| 2005 | 8 | Object Categorization By Learned Universal Visual Dictionary IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). |
J. Winn; A. Criminisi and T. Minka; |
| 2005 | 9 | Detection Of Multiple, Partially Occluded Humans In A Single Image By Bayesian Combination Of Edgelet Part Detectors IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper proposes a method for human detection in crowded scene from static images. |
Bo Wu and R. Nevatia; |
| 2005 | 10 | Learning Object Categories From Google’s Image Search IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. |
R. Fergus; L. Fei-Fei; P. Perona and A. Zisserman; |
| 2005 | 11 | Creating Efficient Codebooks For Visual Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe a scalable acceptance-radius based clusterer that generates better codebooks and study its performance on several image classification tasks. |
F. Jurie and B. Triggs; |
| 2005 | 12 | Geometric Context From A Single Image IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We provide a multiple-hypothesis framework for robustly estimating scene structure from a single image and obtaining confidences for each geometric label. |
D. Hoiem; A. A. Efros and M. Hebert; |
| 2005 | 13 | Detecting Irregularities In Images And In Video IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We address the problem of detecting irregularities in visual data, e.g., detecting suspicious behaviors in video sequences, or identifying salient patterns in images. We pose the problem of determining the validity of visual data as a process of constructing a puzzle: We try to compose a new observed image region or a new video segment (the query) using chunks of data (pieces of puzzle) extracted from previous visual examples (the database ). |
O. Boiman and M. Irani; |
| 2005 | 14 | Efficient Visual Event Detection Using Volumetric Features IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper studies the use of volumetric features as an alternative to popular local descriptor approaches for event detection in video sequences. |
Yan Ke; R. Sukthankar and M. Hebert; |
| 2005 | 15 | Evaluation Of Features Detectors And Descriptors Based On 3D Objects IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. |
P. Moreels and P. Perona; |
| 2003 | 1 | Video Google: A Text Retrieval Approach To Object Matching In Videos IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. |
Sivic and Zisserman; |
| 2003 | 2 | Detecting Pedestrians Using Patterns Of Motion And Appearance IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Novel contributions of this paper include: i) development of a representation of image motion which is extremely efficient, and ii) implementation of a state of the art pedestrian detection system which operates on low resolution images under difficult conditions (such as rain and snow). |
Jones and Snow; |
| 2003 | 3 | Real-time Simultaneous Localisation And Mapping With A Single Camera IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a top-down Bayesian framework for single-camera localisation via mapping of a sparse set of natural features using motion modelling and an information-guided active measurement strategy, in particular addressing the difficult issue of real-time feature initialisation via a factored sampling approach. |
|
| 2003 | 4 | Learning A Classification Model For Segmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a two-class classification model for grouping. |
Ren and Malik; |
| 2003 | 5 | On-line Selection Of Discriminative Tracking Features IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a method for evaluating multiple feature spaces while tracking, and for adjusting the set of features used to improve tracking performance. |
Collins and Liu; |
| 2003 | 6 | Recognizing Action At A Distance IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Our goal is to recognize human action at a distance, at resolutions where a whole person may be, say, 30 pixels tall. |
Mori and Malik; |
| 2003 | 7 | Multiclass Spectral Clustering IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a principled account on multiclass spectral clustering. |
Yu and Shi; |
| 2003 | 8 | Recognising Panoramas IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The problem considered in this paper is the fully automatic construction of panoramas. |
Brown and Lowe; |
| 2003 | 9 | Context-based Vision System For Place And Object Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a context-based vision system for place and object recognition. |
Freeman and Rubin; |
| 2003 | 10 | Fast Pose Estimation With Parameter-sensitive Hashing IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce a new algorithm that learns a set of hashing functions that efficiently index examples relevant to a particular estimation task. |
Viola and Darrell; |
| 2003 | 11 | Preemptive RANSAC For Live Structure And Motion Estimation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: A system capable of performing robust live ego-motion estimation for perspective cameras is presented. The system is powered by random sample consensus with preemptive scoring of … |
|
| 2003 | 12 | Image Parsing: Unifying Segmentation, Detection, And Recognition IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a general framework for parsing images into regions and objects. |
Zhuowen Tu; Xiangrong Chen; Yuille and Zhu; |
| 2003 | 13 | Computing Geodesics And Minimal Surfaces Via Graph Cuts IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce a new segmentation method combining some of their benefits. |
Boykov and Kolmogorov; |
| 2003 | 14 | Natural Image Statistics For Natural Image Segmentation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Building on recent progress in modeling filter response statistics of natural images we integrate a statistical model into a variational framework for image segmentation. |
Heiler and Schnorr; |
| 2003 | 15 | Discriminative Random Fields: A Discriminative Framework For Contextual Interaction In Classification IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this work we present discriminative random fields (DRFs), a discriminative framework for the classification of image regions by incorporating neighborhood interactions in the labels as well as the observed data. |
Sanjiv Kumar and Hebert; |
| 2001 | 1 | Robust Real-time Face Detection IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
P. Viola and M. Jones; |
| 2001 | 2 | A Database Of Human Segmented Natural Images And Its Application To Evaluating Segmentation Algorithms And Measuring Ecological Statistics IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a database containing ‘ground truth’ segmentations produced by humans for images of a wide variety of natural scenes. |
D. Martin; C. Fowlkes; D. Tal and J. Malik; |
| 2001 | 3 | Interactive Graph Cuts For Optimal Boundary & Region Segmentation Of Objects In N-D Images IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we describe a new technique for general purpose interactive segmentation of N-dimensional images. |
Y. Y. Boykov and M. -. Jolly; |
| 2001 | 4 | Lambertian Reflectance And Linear Subspaces IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We prove that the set of all reflectance functions (the mapping from surface normals to intensities) produced by Lambertian objects under distant, isotropic lighting lies close to a 9D linear subspace. |
R. Basri and D. Jacobs; |
| 2001 | 5 | Indexing Based On Scale Invariant Interest Points IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a new method for detecting scale invariant interest points. |
K. Mikolajczyk and C. Schmid; |
| 2001 | 6 | Computing Visual Correspondence With Occlusions Using Graph Cuts IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we present a new method which properly addresses occlusions, while preserving the advantages of graph cut algorithms. |
V. Kolmogorov and R. Zabih; |
| 2001 | 7 | Dynamic Textures IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a novel characterization of dynamic textures that poses the problems of modelling, learning, recognizing and synthesizing dynamic textures on a firm analytical footing. |
S. Soatto; G. Doretto and Ying Nian Wu; |
| 2001 | 8 | BraMBLe: A Bayesian Multiple-blob Tracker IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents two theoretical advances which address this limitation and lead to a robust multiple-person tracking system suitable for single-camera real-time surveillance applications. |
M. Isard and J. MacCormick; |
| 2001 | 9 | Deriving Intrinsic Images From Image Sequences IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We focus on a slightly, easier problem: given a sequence of T images where the reflectance is constant and the illumination changes, can we recover T illumination images and a single reflectance image? |
Y. Weiss; |
| 2001 | 10 | The Earth Mover’s Distance Is The Mallows Distance: Some Insights From Statistics IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We discuss the advantages and disadvantages of both distances, and statistical issues involved in computing them from data. |
E. Levina and P. Bickel; |
| 2001 | 11 | Learning The Semantics Of Words And Pictures IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a statistical model for organizing image collections which integrates semantic information provided by associate text and visual information provided by image features. |
K. Barnard and D. Forsyth; |
| 2001 | 12 | Face Recognition With Support Vector Machines: Global Versus Component-based Approach IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. |
B. Heisele; P. Ho and T. Poggio; |
| 2001 | 13 | The Variable Bandwidth Mean Shift And Data-driven Scale Selection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present two solutions for the scale selection problem in computer vision. |
D. Comaniciu; V. Ramesh and P. Meer; |
| 2001 | 14 | Flux Maximizing Geometric Flows IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Several geometric active contour models have been proposed for segmentation in computer vision. |
A. Vasilevskiy and K. Siddiqi; |
| 2001 | 15 | Matching Shapes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a novel approach to measuring similarity between shapes and exploit it for object recognition. |
S. Belongie; J. Malik and J. Puzicha; |
| 1999 | 1 | Object Recognition From Local Scale-invariant Features IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. |
D. G. Lowe; |
| 1999 | 2 | Fast Approximate Energy Minimization Via Graph Cuts IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we address the problem of minimizing a large class of energy functions that occur in early vision. |
Y. Boykov; O. Veksler and R. Zabih; |
| 1999 | 3 | Flexible Camera Calibration By Viewing A Plane From Unknown Orientations IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Proposes a flexible new technique to easily calibrate a camera. |
Zhengyou Zhang; |
| 1999 | 4 | Texture Synthesis By Non-parametric Sampling IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A non-parametric method for texture synthesis is proposed. |
A. A. Efros and T. K. Leung; |
| 1999 | 5 | Wallflower: Principles And Practice Of Background Maintenance IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We compare our system with 8 other background subtraction algorithms. |
K. Toyama; J. Krumm; B. Brumitt and B. Meyers; |
| 1999 | 6 | A Theory Of Shape By Space Carving IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we consider the problem of computing the 3D shape of an unknown, arbitrarily-shaped scene from multiple photographs taken at known but arbitrarily-distributed viewpoints. |
K. N. Kutulakos and S. M. Seitz; |
| 1999 | 7 | Learning Low-level Vision IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We show a learning-based method for low-level vision problems-estimating scenes from images. |
W. T. Freeman and E. C. Pasztor; |
| 1999 | 8 | Mean Shift Analysis And Applications IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: A nonparametric estimator of density gradient, the mean shift, is employed in the joint, spatial-range (value) domain of gray level and color images for discontinuity preserving … |
D. Comaniciu and P. Meer; |
| 1999 | 9 | Vision In Bad Weather IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Based on this observation, we develop models and methods for recovering pertinent scene properties, such as three-dimensional structure, from images taken under poor weather conditions. |
S. K. Nayar and S. G. Narasimhan; |
| 1999 | 10 | Single View Metrology IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe how 3D affine measurements may be computed from a single perspective view of a scene given only minimal geometric information determined from the image. |
A. Criminisi; I. Reid and A. Zisserman; |
| 1999 | 11 | Segmentation Using Eigenvectors: A Unifying View IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we give a unified treatment of these algorithms, and show the close connections between them while highlighting their distinguishing features. |
Y. Weiss; |
| 1999 | 12 | Real-time Object Detection For smart Vehicles IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents an efficient shape-based object detection method based on Distance Transforms and describes its use for real-time vision on-board vehicles. |
D. M. Gavrila and V. Philomin; |
| 1999 | 13 | Empirical Evaluation Of Dissimilarity Measures For Color And Texture IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper empirically compares nine image dissimilarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. |
J. Puzicha; J. M. Buhmann; Y. Rubner and C. Tomasi; |
| 1999 | 14 | A Probabilistic Exclusion Principle For Tracking Multiple Objects IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Another important contribution of the paper is the presentation of partitioned sampling, a new sampling method for multiple object tracking. |
J. MacCormick and A. Blake; |
| 1999 | 15 | Manhattan World: Compass Direction From A Single Image By Bayesian Inference IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We demonstrate an algorithm for detecting the orientation of the user in such scenes based on Bayesian inference using statistics which we have learnt in this domain. |
J. M. Coughlan and A. L. Yuille; |
| 1998 | 1 | Bilateral Filtering For Gray And Color Images IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: Bilateral filtering smooths images while preserving edges, by means of a nonlinear combination of nearby image values. The method is noniterative, local, and simple. It combines … |
C. Tomasi and R. Manduchi; |
| 1998 | 2 | A Metric For Distributions With Applications To Image Databases IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we focus on applications to image databases, especially color and texture. |
Y. Rubner; C. Tomasi and L. J. Guibas; |
| 1998 | 3 | A General Framework For Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a general trainable framework for object detection in static images of cluttered scenes. |
C. P. Papageorgiou; M. Oren and T. Poggio; |
| 1998 | 4 | Shock Graphs And Shape Matching IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We introduce a novel tree matching algorithm which finds the best set of corresponding nodes between two shock trees in polynomial time. |
K. Siddiqi; A. Shokoufandeh; S. J. Dickenson and S. W. Zucker; |
| 1998 | 5 | Depth Discontinuities By Pixel-to-pixel Stereo IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: An algorithm to detect depth discontinuities from a stereo pair of images is presented. |
S. Birchfield and C. Tomasi; |
| 1998 | 6 | A Maximum-flow Formulation Of The N-camera Stereo Correspondence Problem IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper describes a new algorithm for solving the N-camera stereo correspondence problem by transforming it into a maximum-flow problem. |
S. Roy and I. J. Cox; |
| 1998 | 7 | Color- And Texture-based Image Segmentation Using EM And Its Application To Content-based Image Retrieval IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper we present a new image representation which provides a transformation from the raw pixel data to a small set of image regions which are coherent in color and texture space. |
S. Belongie; C. Carson; H. Greenspan and J. Malik; |
| 1998 | 8 | Parameterized Modeling And Recognition Of Activities IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A framework for modeling and recognition of temporal activities is proposed. |
Y. Yacoob and M. J. Black; |
| 1998 | 9 | Motion Segmentation And Tracking Using Normalized Cuts IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We propose a motion segmentation algorithm that aims to break a scene into its most prominent moving groups. |
Jianbo Shi and J. Malik; |
| 1998 | 10 | A Theory Of Catadioptric Image Formation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we derive the complete class of single-lens single-mirror catadioptric sensors which have a single viewpoint and an expression for the spatial resolution of a catadioptric sensor in terms of the resolution of the camera used to construct it. |
S. Baker and S. K. Nayar; |
| 1998 | 11 | Thresholding For Change Detection IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe four different methods for selecting thresholds that work on very different principles. |
P. Rosin; |
| 1998 | 12 | A Mixed-state Condensation Tracker With Automatic Model-switching IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper presents a significant development of random sampling methods to allow automatic switching between multiple motion models as a natural extension of the tracking process. |
M. Isard and A. Blake; |
| 1998 | 13 | Spatial Color Indexing And Applications IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We suggest the use of the color correlogram as a generic indexing tool to tackle various computer vision problems. |
Jing Huang; S. R. Kumar; M. Mitra and Wei-Jing Zhu; |
| 1998 | 14 | ASL Recognition Based On A Coupling Between HMMs And 3D Motion Analysis IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present a framework for recognizing isolated and continuous American Sign Language (ASL) sentences from three-dimensional data. |
C. Vogler and D. Metaxas; |
| 1998 | 15 | Wide Baseline Stereo Matching IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The objective of this work is to enlarge the class of camera motions for which epipolar geometry and image correspondences can be computed automatically. |
P. Pritchett and A. Zisserman; |
| 1995 | 1 | Geodesic Active Contours IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Previous models of geometric active contours are improved as showed by a number of examples. |
V. Caselles; R. Kimmel and G. Sapiro; |
| 1995 | 2 | Alignment By Maximization Of Mutual Information IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: As applied in this paper, the technique is intensity-based, rather than feature-based. |
P. Viola and W. M. Wells; |
| 1995 | 3 | In Defence Of The 8-point Algorithm IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: The fundamental matrix is a basic tool in the analysis of scenes taken with two uncalibrated cameras, and the 8 point algorithm is a frequently cited method for computing the … |
R. I. Hartley; |
| 1995 | 4 | Gradient Flows And Geometric Active Contour Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we analyze the geometric active contour models discussed previously from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. |
S. Kichenassamy; A. Kumar; P. Olver; A. Tannenbaum and A. Yezzi; |
| 1995 | 5 | Estimating The Tensor Of Curvature Of A Surface From A Polyhedral Approximation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe a method to estimate the tensor of curvature of a surface at the vertices of a polyhedral approximation. |
G. Taubin; |
| 1995 | 6 | Tracking And Recognizing Rigid And Non-rigid Facial Motions Using Local Parametric Models Of Image Motion IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: This paper explores the use of local parametrized models of image motion for recovering and recognizing the non-rigid and articulated motion of human faces. |
M. J. Black and Y. Yacoob; |
| 1995 | 7 | Model-based Tracking Of Self-occluding Articulated Objects IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe a framework for local trading of self occluding motion, in which one part of an object obstructs the visibility of another. |
J. M. Rehg and T. Kanade; |
| 1995 | 8 | Curve And Surface Smoothing Without Shrinkage IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: In this paper, we introduce a new method for smoothing piecewise linear shapes of arbitrary dimension and topology. |
G. Taubin; |
| 1995 | 9 | Probabilistic Visual Learning For Object Detection IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. |
B. Moghaddam and A. Pentland; |
| 1995 | 10 | Face Recognition From One Example View IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We develop example-based techniques for applying the rotation seen in the prototypes to essentially rotate the single real view which is available. |
D. Beymer and T. Poggio; |
| 1995 | 11 | Stochastic Completion Fields: A Neural Model Of Illusory Contour Shape And Salience IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe an algorithm and representation level theory of illusory contour shape and salience. |
L. R. Williams and D. W. Jacobs; |
| 1995 | 12 | Topologically Adaptable Snakes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The paper presents a typologically adaptable snakes model for image segmentation and object representation. |
T. McInerney and D. Terzopoulos; |
| 1995 | 13 | Recognition Of Human Body Motion Using Phase Space Constraints IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A new method for representing and recognizing human body movements is presented. |
L. W. Campbell and A. F. Bobick; |
| 1995 | 14 | Finding Faces In Cluttered Scenes Using Random Labeled Graph Matching IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: An algorithm for locating quasi-frontal views of human faces in cluttered scenes is presented. |
T. K. Leung; M. C. Burl and P. Perona; |
| 1995 | 15 | Mosaic Based Representations Of Video Sequences And Their Applications IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: We describe techniques for the basic elements of the mosaic construction process, namely alignment, integration, and residual analysis. |
M. Irani; P. Anandan and S. Hsu; |
| 1993 | 1 | Enhanced Image Capture Through Fusion IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors present an extension to the pyramid approach to image fusion. |
P. J. Burt and R. J. Kolczynski; |
| 1993 | 2 | A Framework For The Robust Estimation Of Optical Flow IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A graduated non-convexity algorithm is presented for recovering optical flow and motion discontinuities. |
M. J. Black and P. Anandan; |
| 1993 | 3 | Robust Computation Of Optical Flow In A Multi-scale Differential Framework IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors developed an algorithm for computing optical flow in a differential framework. |
J. Weber and J. Malik; |
| 1993 | 4 | Tracking Non-rigid Objects In Complex Scenes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors describe a model-based method for tracking nonrigid objects moving in a complex scene. |
D. P. Huttenlocher; J. J. Noh and W. J. Rucklidge; |
| 1993 | 5 | A Finite Element Model For 3D Shape Reconstruction And Nonrigid Motion Tracking IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors present a physics-based approach for recovering the 3-D shape and tracking the motion of nonrigid objects using a 3-D elastically deformable balloon model. |
T. McInerney and D. Terzopoulos; |
| 1993 | 6 | A Computational Model Of Neural Contour Processing: Figure-ground Segregation And Illusory Contours IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors present a computational model of contour processing that was suggested by neurophysiological recordings from the monkey visual cortex. |
F. Heitger and R. von der Heydt; |
| 1993 | 7 | Extracting Projective Structure From Single Perspective Views Of 3D Point Sets IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: A number of recent papers have argued that invariants do not exist for three-dimensional point sets in general position, which has often been misinterpreted to mean that … |
C. A. Rothwell; D. A. Forsyth; A. Zisserman and J. L. Mundy; |
| 1993 | 8 | Linear And Incremental Acquisition Of Invariant Shape Models From Image Sequences IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: The authors show how to automatically acquire similarity-invariant shape representations of objects from noisy image sequences under a weak perspective. The incremental nature of … |
D. Weinshall and C. Tomas; |
| 1993 | 9 | Robust Structure From Motion Using Motion Parallax IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: An efficient and geometrically intuitive algorithm for reliably interpreting the image velocities of moving objects in 3-D is presented. |
R. Cipolla; Y. Okamoto and Y. Kuno; |
| 1993 | 10 | Fast Segmentation, Tracking, And Analysis Of Deformable Objects IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors present a physically based deformable model which can be used to track and analyze non-rigid motion of dynamic structures in time sequences of 2-D or 3-D medical images. |
C. Nastar and N. Ayache; |
| 1993 | 11 | A Generalized Brightness Change Model For Computing Optical Flow IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Using this model, they describe a method for the computation of optical flow and investigate its performance in a variety of conditions involving brightness variations of scene points, due to illumination nonuniformity, light source motion, specular reflection, and/or interreflection. |
S. Negahdaripour and C. -. Yu; |
| 1993 | 12 | Learning Recognition And Segmentation Of 3-D Objects From 2-D Images IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A framework called Cresceptron is introduced for automatic algorithm design through learning of concepts and rules, thus deviating from the traditional mode in which humans specify the rules constituting a vision algorithm. |
J. J. Weng; N. Ahuja and T. S. Huang; |
| 1993 | 13 | Recovering Reflectance And Illumination In A World Of Painted Polyhedra IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: Such approaches prove inadequate in a 3-D world of painted polyhedra which allows for the existence of discontinuities in both the reflectance and illumination distributions. |
P. Sinha and E. Adelson; |
| 1993 | 14 | Diagonal Transforms Suffice For Color Constancy IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The overall goal is to present a theoretical analysis connecting many established theories of color constancy. |
G. D. Finlayson; M. S. Drew and B. V. Funt; |
| 1993 | 15 | Shape From Texture From A Multi-scale Perspective IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: The problem of scale in shape from texture is addressed. The need for two scale parameters is emphasized: a local scale, for describing the amount of smoothing used for … |
T. Lindeberg and J. Garding; |
| 1990 | 1 | Dynamic 3D Models With Local And Global Deformations: Deformable Superquadrics IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A physically-based approach is presented to fitting complex 3D shapes using a novel class of dynamic models. |
D. Terzopoulos and D. Metaxas; |
| 1990 | 2 | Indexing Via Color Histograms IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors introduce a technique called histogram intersection for efficiently matching model and image histograms. |
M. J. Swain and D. H. Ballard; |
| 1990 | 3 | Shape From Interreflections IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: An iterative algorithm is presented that simultaneously recovers the actual shape and the actual reflectance from the pseudo estimates. |
S. K. Nayar; K. Ikeuchi and T. Kanade; |
| 1990 | 4 | Detecting And Localizing Edges Composed Of Steps, Peaks And Roofs IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: The projection of depth or orientation discontinuities in a physical scene results in image intensity edges which are not ideal step edges but are more typically a combination of … |
P. Perona and J. Malik; |
| 1990 | 5 | Matching Range Images Of Human Faces IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: To establish the optimal correspondence, a graph matching algorithm is applied. |
J. C. Lee and E. Milios; |
| 1990 | 6 | A Locally Adaptive Window For Signal Matching IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors presents a signal matching algorithm that can select an appropriate window size adaptively so as to obtain both precise and stable estimation of correspondences. |
M. Okutomi and T. Kanade; |
| 1990 | 7 | Pose Determination From Line-to-plane Correspondences: Existence Condition And Closed-form Solutions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The author describes a polynomial method that, unlike previous methods, does not require prior knowledge about the location of the object. |
H. H. Chen; |
| 1990 | 8 | A Fast Algorithm For Active Contours IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A method of controlling snakes that combines speed, flexibility, and simplicity is presented. |
D. J. Williams and M. Shah; |
| 1990 | 9 | An Estimation-theoretic Framework For Image-flow Computation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A novel framework for computing image flow from time-varying imagery is described. |
A. Singh; |
| 1990 | 10 | BONSAI: 3D Object Recognition Using Constrained Search IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: A description is presented of BONSAI, a model-based 3-D object recognition system, which identifies and localizes 3-D objects in range images of one or more parts which have been … |
P. J. Flynn and A. K. Jain; |
| 1990 | 11 | The 2.1-D Sketch IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: A model is described for image segmentation that tries to capture the low-level depth reconstruction exhibited in early human vision, giving an important role to edge terminations. |
M. Nitzberg and D. Mumford; |
| 1990 | 12 | From Uncertainty To Visual Exploration IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: The question posed is what can be inferred from ambiguity in processes of visual interpretation? Much emphasis is naturally placed on the form of constraints used to minimize … |
P. Whaite and F. P. Ferrie; |
| 1990 | 13 | A Finite Element Method Applied To New Active Contour Models And 3D Reconstruction From Cross Sections IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors present a model of deformation which solves some of the problems encountered with the original method such as instability and initial data while reducing the computational complexity. |
L. D. Cohen and I. Cohen; |
| 1990 | 14 | The Dynamic Analysis Of Apparent Contours IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Highlight: The authors develop previous theories of the analysis of deformation of apparent contours under viewer motion. |
R. Cipolla and A. Blake; |
| 1990 | 15 | Vanishing Point Calculation As A Statistical Inference On The Unit Sphere IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save Abstract: An examination is made of vanishing point calculation as a statistical estimation problem. It is assumed that image line segments have been previously clustered into groups of … |
R. T. Collins and R. S. Weiss; |
| 1988 | 1 | Geometric Hashing: A General And Efficient Model-based Recognition Scheme IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
Y. Lamdan and H. J. Wolfson; |
| 1988 | 2 | Structural Saliency: The Detection Of Globally Salient Structures Using A Locally Connected Network IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
A. Sha’asua and S. Ullman; |
| 1988 | 3 | An Adaptive Clustering Algorithm For Image Segmentation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
T. N. Pappas and N. S. Jayant; |
| 1988 | 4 | On The Sensitivity Of The Hough Transform For Object Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
W. E. L. Grimson and D. P. Huttenlocher; |
| 1988 | 5 | Using Dynamic Programming For Minimizing The Energy Of Active Contours In The Presence Of Hard Constraints IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
A. A. Amini; S. Tehrani and T. E. Weymouth; |
| 1988 | 6 | Parallel Depth Recovery By Changing Camera Parameters IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
M. Subbarao; |
| 1988 | 7 | Efficiently Computing And Representing Aspect Graphs Of Polyhedral Objects IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
Z. Gigus; J. Canny and R. Seidel; |
| 1988 | 8 | Modal Control Of An Attentive Vision System IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
J. J. Clark and N. J. Ferrier; |
| 1988 | 9 | Shape Information From Shading: A Theory About Human Perception IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
A. Pentland; |
| 1988 | 10 | Organization Of Smooth Image Curves At Multiple Scales IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
D. G. Lowe; |
| 1988 | 11 | Optimal Corner Detector IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
K. Rangarajan; M. Shah and D. van Brackle; |
| 1988 | 12 | The Motion Coherence Theory IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
A. L. Yuille and N. M. Grzywacz; |
| 1988 | 13 | The Combinatorics Of Object Recognition In Cluttered Environments Using Constrained Search IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
W. E. L. Grimson; |
| 1988 | 14 | The Organization Of Curve Detection: Coarse Tangent Fields And Fine Spline Coverings IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
S. W. Zucker; C. David; A. Dobbins and L. Iverson; |
| 1988 | 15 | Robust Window Operators IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Save |
P. J. Besl; J. B. Birch and L. T. Watson; |