Workshop description

In recent years, the security of face recognition systems has been increasingly threatened. Face Anti-spoofing (FAS) is essential to secure face recognition systems primarily from various attacks. In order to attract researchers and push forward the state of the art in Face Presentation Attack Detection (PAD), we organized three editions of Face Anti-spoofing Workshop and Competition at CVPR 2019, CVPR 2020, and ICCV 2021, which have attracted more than 800 teams from academia and industry, and greatly promoted the algorithms to overcome many challenging problems. However, long-distance face presentation attack based on surveillance scene is still a threat. Specifically, compared with FAS in traditional scenes such as phone unlocking, face payment, and self-service security inspection, FAS in long-distance such as station squares, parks, and self-service supermarkets are equally important, but it has not been sufficiently explored yet. With the goal of giving continuity to our effort in this relevant problem, we are proposing the fourth edition of the Face Anti-Spoofing Workshop and Challenge@CVPR 2023. Unlike the previous editions, where faces were identified by posing in specific situations at a close distance, the 2023 challenge will focus on more general surveillance scenarios, and alleviating the performance degradation of PAD technology in the case of low face resolution, occlusion interference, non-frontal perspective, and other natural person behaviors. Fully considering the above difficulties and challenges, a large-scale High Fidelity Mask dataset based on Surveillance Scenes, namely SuHiFiMask, is released for this fourth edition for algorithm design and competition promotion. For more information about the workshop, pleses visit the main Face Anti-spoofing Workshop webpage.


There are no news registered in