The Visual Big Data Research Center researches face recognition algorithms, facial expression, depression, personality and other facial attribute discrimination algorithms, and face-changing algorithms based on generative adversarial networks and diffusion models, and face generation algorithms based on text descriptions.

The face recognition algorithm has won the second place in the ICPR accuracy test. The latest 200-layer neural network face recognition algorithm has an accuracy rate of 99.27% and 99.19% in the MegaFace million test 1:N and 1:1, respectively, reaching the highest in the industry. The overall performance of the face mask test of MFR Ongoing Challenge exceeds 98%, which is also the highest in the industry currently.

The face motion unit detection algorithm won the second place in the academic group of the 5th face motion unit detection challenge of CVPR 2023!