The Conference on Computer Vision and Pattern Recognition is an annual conference on computer vision and pattern recognition. As ranked by Google Scholar's h-index metric in 2015, CVPR is the number one venue in Computer Vision and number seven in Engineering and Computer Science. It also has the highest h-index of any conference in any field, is the leading IEEE publications including journals, and it is ranked in the top 70 of all publications. According to Microsoft Academic Search by 2014 there were over 169,936 citations to CVPR papers. It is also highly ranked by various government agencies: It has an 'A' rating from the Australian Ranking of ICT Conferences and an 'A1' rating from the Brazilian ministry of education(Qualis (2012)).
CVPR was first held in Washington DC in 1983 by Takeo Kanade and Dana Ballard (previously the conference was named Pattern Recognition and Image Processing). From 1985-2010 it was sponsored by the IEEE Computer Society. In 2011 it was co-sponsored by the IEEE Computer Society and by University of Colorado Colorado Springs. Since 2012 it has been co-sponsored by IEEE Computer Society and the Computer Vision Foundation(CVF). CVF now provides open access to the conference papers.
CVPR considers a wide range of topics related to computer vision and pattern recognition—basically any topic that is extracting structures or answers from images or video or applying mathematical methods to data to extract or recognize patterns. Each year the conference has an explicit list of topics for that year. The conference event also includes a wide range of workshops and tutorials. Each year multiple company also donate funds to support the conference and many of those also exhibit at the conference.
The conference is highly selective with generally < 30% acceptance rates for all papers and < 5% for oral presentations. The conference is managed by a rotating group of volunteers—with are chosen in a public election at the PAMI-TC meeting 3 years before the meeting. CVPR uses a multi-tier double-blind review process. The program chairs (who cannot submit papers), select 50-60 area chairs who manage the reviewers for their subset of reviewers. There are generally 3 or more reviewers per paper. The Area chairs discuss the paper with the reviewers then among the Acs and finally produce a meta-review and make a recommendation the program chairs who make final decisions.
The conference is held in June and rotates around the US generally West, Central and East. In 2013 the conference was in Portland OR. In 2014 the conference was held in Columbus Ohio with over 1900 attendees. In 2015 it was in Boston MA. In 2016 it was in Las Vegas NV. In 2017 it will be in Honolulu HI.
These awards are picked by committees delegated by the program chairs of the conference.
Awarded at CVPR 2016:Best Paper: Deep Residual Learning for Image Recognition, Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian SunBest Student Paper: Structural-RNN: Deep Learning on Spatio-Temporal Graphs, Ashesh Jain, Amir R. Zamir, Silvio Savarese, Ashutosh SaxenaBest Paper Honorable Mention: Sublabel-Accurate Relaxation of Nonconvex Energies., Thomas Möllenhoff, Emanuel Laude, Michael Moeller, Jan Lellmann, Daniel CremersAwarded at CVPR 2015:Best Paper: DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time Richard, A. Newcombe, Dieter Fox, Steven M. SeitzBest Student Paper: Category-Specific Object Reconstruction from a Single Image, Abhishek Kar, Shubham Tulsiani, João Carreira, Jitendra MalikBest Paper Honorable Mention: Efficient Globally Optimal Consensus Maximisation with Tree Search, Tat-Jun Chin, Pulak Purkait, Anders Eriksson, David SuterBest Paper Honorable Mention: Fully Convolutional Networks for Semantic Segmentation, Jonathan Long, Evan Shelhamer, Trevor DarrellBest Paper Honorable Mention: Picture: A Probabilistic Programming Language for Scene Perception, Tejas D Kulkarni, Pushmeet Kohli, Joshua B Tenenbaum, Vikash MansinghkaAwarded at CVPR 2014:Best Paper: What Camera Motion Reveals About Shape with Unknown BRDF, Manmohan ChandrakerBest Paper Runner-Up: 3D Shape and Indirect Appearance by Structured Light Transport, Matthew O'Toole, John Mather, Kyros KutulakosBest Student Paper: Partial Optimality by Pruning for MAP-inference with General Graphical Models, Paul Swoboda, Bogdan Savchynskyy, Joerg Kappes, Christoph SchnörrOutstanding Demo: Real-Time Video Magnification, Neal Wadhwa, Michael Rubinstein, Frédo Durand, William T. FreemanHonorable Mention Demo: Learning to be a Depth Camera, Sean Ryan Fanello, Cem Keskin, Shahram Izadi, Pushmeet Kohli, David Kim, David Sweeney, Antonio Criminisi, Jamie Shotton, Sing Bing Kang, Tim PaekAwarded at CVPR 2013:Best Paper: Fast, Accurate Detection of 100,000 Object Classes on a Single Machine, Thomas Dean, Jay Yagnik, Mark Ruzon, Mark Segal, Jonathon Shlens, and Sudheendra VijayanarasimhanBest Paper Runner-Up: Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization, Marcus Brubaker, Andreas Geiger, and Raquel UrtasunBest Student Paper: Discriminative Non-blind Deblurring, Uwe Schmidt, Carsten Rother, Sebastian Nowozin, Jeremy Jancsary, and Stefan RothAwarded at CVPR 2012:Best Paper: A Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization, Yuchao Dai, Hongdong Li, Mingyi HeBest Student Paper: Max-Margin Early Event Detectors, Minh Hoai, Fernando De la TorreAwarded at CVPR 2011:Best Paper: Real-time Human Pose Recognition in Parts from Single Depth Images, Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew BlakeBest Paper Honorable Mention: Discrete-Continuous Optimization for Large-scale Structure from Motion, David Crandall, Andrew Owens, Noah Snavely, Daniel HuttenlocherBest Student Paper: Recognition Using Visual Phrases, Ali Farhadi, Mohammad Amin SadeghiBest Student Paper Honorable Mention: Separating Reflective and Fluorescent Components of An Image, Cherry Zhang, Imari SatoAwarded at CVPR 2010:Best Paper: Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data using the L1 Norm, Anders Eriksson and Anton van den HengelBest Student Paper: Visual Event Recognition in Videos by Learning from Web Data, Lixin Duan, Dong Xu, Wai-Hung Tsang, and Jiebo LuoBest Student Paper Honorable Mention: Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities, Bangpeng Yao and Li Fei-FeiAwarded at CVPR 2009:Best Paper: Single Image Haze Removal Using Dark Channel Prior, Kaiming He, Jian Sun, Xiaoou TangBest Paper Honorable Mention: Understanding and evaluating blind deconvolution algorithms, Anat Levin, Yair Weiss, Fredo Durand, Bill FreemanBest Student Paper: Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment, Ce Liu, Jenny Yuen, Antonio TorralbaBest Student Paper Honorable Mention: A Tensor-Based Algorithm for High-Order Graph Matching, Olivier Duchenne, Francis Bach, In So Kweon, Jean PonceAwarded at CVPR 2008Best Paper: Beyond Sliding Windows: Object Localization by Efficient Subwindow Search, Christoph H. Lampert, Matthew B.Blaschko,Thomas HofmannBest Paper: Global Stereo Reconstruction under Second Order Smoothness Priors, Oliver Woodford, Ian Reid, Philip Torr, Andrew FitzgibbonBest Student Paper: Fast Image Search for Learned Metrics, Prateek Jain, Brian Kulis, Kristen GraumanAwarded at CVPR 2007Best Paper: Dynamic 3D Scene Analysis from a Moving Vehicles, Bastian Leibe, Nico Cornelis, Kurt Cornelis, and Luc Van GoolBest Paper Honorable Mention: Spectral Matting, Anat Levin, Alex Rav-Acha, and Dani LischinskiBest Paper Honorable Mention: Human Detection via Classification on Riemannian Manifolds, Oncel Tuzel, Fatih Porikli, and Peter MeerBest Student Paper: Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Life Spans, Yuan Li, Haizhou Ai, Takayoshi Yamashita, Shihong Lao, and Masato KawadeAwarded at CVPR 2006Best Paper: Putting Objects in Perspective, Derek Hoiem, Alexei Efros, Martial HebertBest Paper Honorable Mention:Incremental learning of object detectors using a visual shape alphabet, Andreas Opelt, Axel Pinz, Andrew ZissermanAwarded at CVPR 2005Best Paper: Real-Time Non-Rigid Surface Detection, Julien Pilet, Vincent Lepetit, Pascal FuaBest Paper Honorable Mention: A Non-Local Algorithm for Image Denoising, Antoni Buades, Bartomeu Coll, Jean-Michel MorelBi-Layer Segmentation of Binocular Stereo Video, Vladimir Kolmogorov, Antonio Criminisi, Andrew Blake, Geoffrey Cross, Carsten RotherVideo Epitomes, Vincent Cheung, Brendan J. Frey, Nebojsa JojicAwarded at CVPR 2004Best Paper: Programmable Imaging using a Digital Micromirror Array, Shree K Nayar, Vlad Branzoi, Terrance E BoultBest Student Paper:Unsupervised learning of image manifolds by semidefinite programming Killeen Q. Weinberger and Lawrence K. Saul.Awarded at CVPR 2003Best Paper: Object Class Recognition by Unsupervised Scale-Invariant Learning, Rob Fergus, Pietro Perona, and Andrew ZissermanBest Paper Honorable Mention: Constraint on Five Points in Two Images, Tomas WernerBest Student Paper: Vector-Valued Image Regularization with PDE's: A Common Framework for Different Applications, David Tschumperle and Rashid DericheAwarded at CVPR 2001Best Paper: Morphable 3D models from video, Matthew BrandBest Paper Runner Up: Robust on-line appearance models for visual tracking, A. Jepson, D. Fleet, T.F. El-MaraghiBest Student Paper: Tracking and modeling non-rigid objects with rank constraints, L. Torresani, D. Yang, E. Alexander, C. BreglerOutstanding Student Paper: Dense image matching with global and local statistical criteria: a variational approach, G. Hermosillo, O. FaugerasOutstanding Student Paper: JPDAF based HMM for real-time contour tracking, Y. Chen, Y. Rui, T. HuangOutstanding Student Paper: Model-based curve evolution techniques for image segmentation, A. Tsai, A. Yezzi, W. Wells, C. Tempany, D. Tucker, A. Fan, E. Grimson, A. WillskyAwarded at CVPR 2000Best Paper: Real-Time Tracking of Non-Rigid Objects using Mean Shift, D. Comaniciu, V. Ramesh, P. MeerBest Paper Runner Up: A New Algorithm for Non-Rigid Point Matching, H. Chui, A. RangarajanBest Student Paper: Statistical Shape Influence in Geodesic Active Contours, M. Leventon, E. Grimson, O. FaugerasThe Longuet-Higgins Prize recognizes CVPR papers from ten years ago that have made a significant impact on computer vision research.
The Pattern Analysis and Machine Intelligence (PAMI) Young Researcher Award is an award given by the Technical Committee on Pattern Analysis and Machine Intelligence (TCPAMI) of the IEEE Computer Society at the CVPR to a researcher within 7 years of completing their Ph.D. for outstanding early career research contributions. Candidates are nominated by the computer vision community, with winners selected by a committee of senior researchers in the field. This award was originally instituted in 2012 by the Elsevier journal Image and Vision Computing, also presented at the CVPR, and the ICV continues to sponsor the award.
2016: Abhinav Gupta and Ce Liu2015: John Wright2014: Derek Hoiem and Jamie Shotton2013: Anat Levin and Kristen Grauman2012 (as the IVC Outstanding Young Researcher Award): Deva Ramanan