Long Beach, California—The CVPR 2019 Conference, the premier event for the artificial intelligence and computer vision technologies behind such innovations as facial recognition and self-driving cars, broke several of its records at this week’s annual gathering:
- Record attendance at 9,227 registrants, so many in fact that the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), as it’s formally called, had to close additional registrations. The Long Beach Convention Center, where the conference is being held 16-20 June 2019, could not accommodate any more participants. In all, attendees came from 68 countries. The next highest attendance was last year’s conference, with 6,128 participants. Organizers attribute the explosive 51% growth to social media and autonomous systems—all using computer vision tech.
- Record number of industry exhibitors at 181, including tech titans such as Apple, Amazon, Facebook, Google, Microsoft, IBM, Huawei, and Tencent. As such, the conference also posted record corporate sponsorships valued at $3.1 million. The growth has been remarkable considering that in 1988, the conference didn’t have a single industry sponsor, organizers said. Last year’s exhibitors numbered 149.
- Record paper submissions at 5,160—a 56 percent increase over 2018. Only 1,294 of those research papers were accepted at the conference, for a 25.2 percent acceptance rate.
“I would have never imagined that we would have grown to a community of this size,” said CVPR General Chair Song-Chun Zhu, also a professor at the University of California, Los Angeles. As such, the CVPR event is now one of tech’s top artificial intelligence conferences, ranked among Google Scholar’s Top 10 publications for the quality of research papers presented at the gathering.
General Welcome and the Organizing Committee
Where All the CVPR 2019 Participants Came From
“Europe has contributed from almost every country,” Zhu said about the origins of CVPR 2019 Conference attendees. Most came from the United States, at 4,743. China was next at 1,044.
Explosive Growth in Paper Submissions: 10.8 Billion by 2028?
This year’s record paper submissions were so enormous that organizers wondered about the future.
“If we say that this 26 percent acceleration of growth were to continue for another nine years, then we’d have 10.8 billion submitted papers in 2028: That’s one for every man, woman, and child,” Program Chair Derek Hoiem, also an associate professor at the University of Illinois at Urbana-Champaign.
The audience laughed.
CVPR Award Winners
Several award winners were announced:
Best Paper: Shumian Xin, Sotiris Nousias, Kyros Kutulakos, Aswin Sankaranarayanan, Srinivasa G. Narasimhan, and Ioannis Gkioulekas for their “A Theory of Fermat Paths for Non-Line-of-Sight Shape Reconstruction.” The authors are from Carnegie Mellon University, University of Toronto, and University College London.
Best Paper, Honorable Mention: Tero Karras, Samuli Laine, and Timo Aila for their “A Style-Based Generator Architecture for Generative Adversarial Networks.”
Best Paper, Honorable Mention: Zhengqi Li, Tali Dekel, Forrester Cole, Richard Tucker, Ce Liu, Bill Freeman, and Noah Snavely for their “Learning the Depths of Moving People by Watching Frozen People.”
Best Student Paper: Xin Wang, Qiuyan Huang, Asli Celikyilmaz, Jianfeng Gao, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, and Lei Zhang for their “Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation.”
PAMI Longuet-Higgins Prize
Technical Committee on Pattern Analysis and Machine Intelligence (TCPAMI) Chair Bryan Morse announced the winner of the PAMI Longuet-Higgins Prize, which is awarded to the “retrospective most impactful paper from CVPR 2009.” It is akin to a seminal work that achieves a “test-of-time” status. The TCPAMI is an IEEE Computer Society community of volunteers who organize the CVPR Conference.
The paper to win the prize was “ImageNet: A large-scale hierarchical image database” by Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei.
Meanwhile, the PAMI Young Researcher Award went to Karen Simonyan, who couldn’t attend the conference, Morse said.
The final award of the event was given, as it turned out, to Morse himself, who received the IEEE Computer Society Technical and Conference Activities Board 2019 Distinguished Leadership Award “for outstanding and sustained contributions to the pattern analysis and machine intelligence community and the IEEE Computer Society Technical & Conference Activities Board.” Morse is also a professor at Brigham Young University.
The Computer Society’s 2020 president, Leila De Floriani, exercised the honors of handing the award to Morse.
How CVPR Attracts an Audience
A full house inside the Terrace Theater applauded the recording-breaking news and the awards given to the finest minds in the field of computer vision at the CVPR 2019 Conference.
Read more related articles about CVPR:
- How CVPR 2019 Conference — Tech’s Premier Event for Computer Vision — Broke Records on All Fronts. Cite Self-Driving Cars and Your Social Media Apps, says Finance Co-Chair Walter Scheirer
- Oral Presentations of Papers at the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Poster Sessions Provoke Deep Discussions at the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Industry Exhibitors Take Over Hundreds of Thousands of Square Feet at the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Tutorials Detail Advances in Robotics, AR/VR, and Self-Driving Cars at the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Workshops of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
About Michael Martinez
Michael Martinez, the editor of the Computer Society’s Computer.Org website and its social media, has covered technology as well as global events while on the staff at CNN, Tribune Co. (based at the Los Angeles Times), and the Washington Post. He welcomes email feedback, and you can also follow him on LinkedIn.