Detecting Facial Action Units From Global-Local Fine-Grained Expressions

• Published in: IEEE transactions on circuits and systems for video technology Vol. 34; no. 2; pp. 983 - 994
• Main Authors: Zhang, Wei, Li, Lincheng, Ding, Yu, Chen, Wei, Deng, Zhigang, Yu, Xin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Action units; Annotations; Datasets; deep learning; Detection algorithms; Embedding; expression embedding; Face recognition; facial expression; Feature extraction; Image reconstruction; Labels; Three-dimensional displays; Training; Transformers

Since Facial Action Unit (AU) annotations require domain expertise, common AU datasets only contain a limited number of subjects. As a result, a crucial challenge for AU detection is addressing identity overfitting. We find that AUs and facial expressions are highly associated, and existing facial e...