International Conference on Computer Vision

International Conference on Computer Vision
Name	International Conference on Computer Vision
Abbreviation	ICCV
Discipline	Computer vision
Publisher	IEEE
Frequency	Biennial (historically), now annual cycle rotation with CVPR/ ECCV
First	1987
Country	International

Contents

International Conference on Computer Vision The International Conference on Computer Vision is a major academic conference in the field of computer vision and computer science that brings together researchers from leading institutions such as Massachusetts Institute of Technology, Stanford University, University of Oxford, University of Toronto and Tsinghua University alongside industry labs including Google Research, Microsoft Research, Facebook AI Research, IBM Research and NVIDIA. Established amid developments at venues like the IEEE Conference on Computer Vision and Pattern Recognition and influenced by workshops at NeurIPS and ICML, the conference features peer-reviewed proceedings and has shaped work across topics represented at gatherings such as CVPR, ECCV, ACL, and ICASSP.

History

ICCV originated following early vision meetings influenced by groups at MIT Media Lab, Carnegie Mellon University, University of Cambridge, and University of California, Berkeley and was first convened during an era marked by milestones like ImageNet and algorithmic advances from labs such as Bell Labs and PARC. Over successive editions hosted in cities including Kyoto, Beijing, Barcelona, Venice and Seoul, ICCV evolved alongside breakthroughs reported at SIGGRAPH, AAAI, IJCAI, and KDD. Steering committees and program chairs have frequently involved faculty from Caltech, ETH Zurich, Peking University, University of Washington, and University College London collaborating with societies such as the IEEE Computer Society and research consortia like OpenAI and DeepMind.

ICCV covers a range of technical areas intersecting work at Stanford AI Lab, MIT CSAIL, Google DeepMind, Facebook AI Research, and Microsoft Research Cambridge. Topics commonly addressed include image recognition pioneered by teams behind AlexNet and ResNet, object detection advanced by research at Toyota Technological Institute at Chicago and ETH Zurich, 3D reconstruction related to projects at Max Planck Institute for Informatics and ETH Zurich, video understanding connected to efforts at Netflix Research and YouTube Research, and multimodal learning explored by groups at University of Toronto and Carnegie Mellon University. ICCV also highlights work on datasets and benchmarks like ImageNet, COCO, KITTI, Cityscapes, and MPII Human Pose Dataset developed in collaboration with institutions such as Facebook AI and Google Research.

The conference program mirrors organizational patterns used by NeurIPS and ICLR, featuring oral presentations, poster sessions, tutorials from labs at Imperial College London and University of Oxford, and workshops sponsored by entities like IEEE and ACM. Proceedings are published in association with the IEEE Computer Society and are indexed alongside publications from CVPR and ECCV in digital libraries maintained by IEEE Xplore and libraries at ACM Digital Library. Program committees draw reviewers from Princeton University, University of Michigan, Columbia University, Harvard University, and corporate labs including Amazon Research and Apple ML Research.

ICCV has hosted seminal works that influenced subsequent papers at CVPR and NeurIPS, including influential architectures analogous to AlexNet, innovations in feature descriptors linked to research from Microsoft Research and Brown University, and key advances in scene understanding connected to teams at Brown University, University of California, San Diego, and Cornell University. Landmark contributions presented at ICCV have catalyzed tools and datasets used by projects at Google Research, Facebook AI Research, OpenAI, and industrial partners such as Tesla and Waymo. The conference has also been the venue for methodological advances that later appeared in journals like IEEE Transactions on Pattern Analysis and Machine Intelligence and collaborations among researchers at Bell Labs, Mitsubishi Electric Research Laboratories, and Siemens.

ICCV confers best paper awards and recognition comparable to prizes at NeurIPS and SIGGRAPH, and laureates often include researchers affiliated with Massachusetts Institute of Technology, Stanford University, University of Oxford, ETH Zurich, and Peking University. Honorees have gone on to receive broader accolades such as the Turing Award, the IEEE Fellow distinction, and society awards administered by the IEEE Computer Society and AAAI. Workshops and demo tracks recognize contributions from corporate research teams at Google DeepMind, Microsoft Research, Facebook AI Research, and independent groups like OpenAI.

ICCV is organized by conference chairs drawn from academia and industry—often faculty at University of California, Berkeley, Carnegie Mellon University, University of Toronto, and researchers from Google Research and Microsoft Research—and coordinated with publishers and societies including the IEEE Computer Society and the Association for Computing Machinery. Sponsors have included technology companies such as NVIDIA, Intel, Google, Microsoft, Facebook, Amazon Web Services, and research funding agencies and foundations including National Science Foundation, European Research Council, Chinese Academy of Sciences, and private endowments linked to institutions like Stanford University and MIT.

Category:Computer vision conferences