Unconstrained facial action unit detection via latent feature domain

• Main Authors: Shao, Zhiwen, Cai, Jianfei, Cham, Tat-Jen, Lu, Xuequan, Ma, Lizhuang
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Unconstrained Facial AU Detection; Domain Adaptation
• Online Access: https://hdl.handle.net/10356/172649
• Institution: Nanyang Technological University

Facial action unit (AU) detection in the wild is a challenging problem, due to the unconstrained variability in facial appearances and the lack of accurate annotations. Most existing methods depend on either impractical labor-intensive labeling or inaccurate pseudo labels. In this paper, we propo...