JYJingyi Yang

Jingyi Yang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jingyi Yang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • G2V2former: Graph Guided Video Vision Transformer for Face Anti-Spoofing

    by Jingyi Yang, Zitong Yu, Jia He, Xiuming Ni, Liepiao Zhang, Hui Li, Xiaochun Cao

    In videos containing spoofed faces, we may uncover the spoofing evidence based on either photometric or dynamic abnormality, or a combination of both. Prevailing face antispoofing (FAS) approaches generally concentrate on the singleframe scenario; however, purely photometric-driven methods overlook the dynamic spoofing clues that may be exposed over time. This may lead FAS systems to conclude incorrect judgments, especially in cases where it is easily distinguishable in terms of dynamics but challenging to discern in terms of photometrics. To this end, we propose the Graph Guided Video Vision Transformer (G2V2former), which combines faces with facial landmarks for the fusion of photometric and dynamic features. We factorize the attention into space and time and fuse them via a spatiotemporal block. Specifically, we design a novel temporal attention, called Kronecker temporal attention, which has a wider receptive field and is beneficial for capturing dynamic information. Moreover, we leverage the low-semantic motion of facial landmarks to guide the high-semantic change of facial expressions based on the motivation that regions containing landmarks may reveal more dynamic clues. Extensive experiments on nine benchmark datasets demonstrate that our method achieves superior performance under various scenarios. The codes will be released at https://github.com/yjyddq/GVformer.