Ant Group joins hands with CVPR22 Workshop to hold visual intelligence competition, with more than 1,300 teams signing up

On June 19, the 17th IEEE ComputerSociety Workshop on Biometrics (CVPR22 17th IEEE ComputerSociety Workshop on Biometrics) and the Ant Group jointly hosted the Visual Intelligence Dual Track Competition concluded successfully.

This competition was held at the CVPR22 Workshop by Ant Group, Fudan University, China Academy of Information and Communications Technology, and Nanyang Technological University in Singapore. It attracted more than 1,300 teams from around the world to sign up for the competition. The competition is divided into two tracks, namely "Pet Biometric Identification" and "Image Tampering Detection". Among them, the "Pet Biometric Identification" competition topic appeared for the first time in an authoritative competition in the field of visual technology. In the end, teams from Huazhong University of Science and Technology, Shanghai University of Science and Technology, and Nanjing University of Science and Technology won the top three in the "Pet Biometric Identification Competition", and teams from NetEase, ByteDance, and Meituan won the top three in the "Image Tampering Detection Competition."

CVPR is organized by the IEEE (Institute of Electrical and Electronics Engineers). It is a world-class conference in the field of computer vision and model recognition, a platform for displaying cutting-edge scientific and technological achievements and exploring academic applications. Ant Group has been deeply involved in computer vision for many years. As of 2022, it has participated in the formulation and release of more than 30 domestic and foreign standards related to the field of computer vision. This year, it published more than ten papers in CVPR.

#The two questions are both topics that have attracted much attention in the current society. With the rapid growth of the pet economy, AI technology empowering the pet industry has gradually become a hot spot in the industry. Related technologies also have high application value in scenarios such as copyright protection and anti-fraud. As an industry leader in this field, Ant Group has previously accumulated a large amount of technology application experience and applied for more than 20 related patents. This time, Ant teamed up with the Artificial Intelligence Innovation and Industry Research Institute of Fudan University to open up its own samples, build a pet-related academic competition platform, and bring the pet nose print recognition competition to CVPR for the first time. In the end, teams from Huazhong University of Science and Technology, Shanghai University of Science and Technology and Nanjing University of Science and Technology won the top three with AUC points of 0.9087 (the closer the AUC is to 1.0, the higher the accuracy of the algorithm's judgment), 0.8881 points and 0.8667 points respectively.

Qi Yuan, Distinguished Professor Hao Qing of Fudan University and Dean of the Institute of Artificial Intelligence Innovation and Industry, said that the original intention of this competition is to provide outstanding algorithm talents from universities and enterprises with data and competition close to real scenarios. Questions, so that everyone can compete and communicate on this platform, and explore the possibility of cutting-edge technology to solve real-world problems. The solutions of the winning teams in this pet noseprint recognition competition have been open sourced.

# Behind the image tampering detection technology is the deeply discussed issue of deep forgery. The tampered and synthesized images are often used in illegal content and fake news to induce public opinion, which not only infringes on personal privacy, but also disrupts social order. Ant Group, together with Nanyang Technological University of Singapore and China Academy of Information and Communications Technology, held an image tampering detection competition to promote the progress and development of detection technology. In the end, teams from NetEase, ByteDance, and Meituan won the top three with AUC points of 0.9938, 0.9913, and 0.9879 respectively.

Liu Shuo, deputy director of the Content Technology Department of the China Academy of Information and Communications Technology’s Cloud Institute, said that the digital age has arrived, and detection technology for counterfeit digital images and videos has become increasingly important. This CVPR 2022 image tampering detection competition inspired technological innovation and provided useful reference for the implementation of technology in real scenarios. In the future, the "offense and defense" surrounding counterfeiting and identification will continue to exist. In addition to the need for continuous technological innovation, it is also necessary to unite "government, industry, academia, research and application" and other parties to jointly explore a practical paradigm for the governance of counterfeit content.

Ant Group has been cooperating with universities in the field of artificial intelligence to develop basic technologies for many years. It has established joint laboratories and other projects with Berkeley, Tsinghua University, Peking University, Chinese Academy of Sciences, Zhejiang University and other Chinese and foreign universities to jointly build an industry-university-research ecosystem. This time, Ant joined hands with domestic and foreign research institutions to hold the CVPR22 Workshop dual competition "for real scenarios", focusing on applying academic research to industry applications, facing real problems and challenges in business scenarios, and promoting the use of cutting-edge technologies to solve real problems through the combination of industry and research. .

The above is the detailed content of Ant Group joins hands with CVPR22 Workshop to hold visual intelligence competition, with more than 1,300 teams signing up. For more information, please follow other related articles on the PHP Chinese website!