A novel dual-channel graph convolutional neural network for facial action unit recognition

Download PDF
Open Webpage

Xibin Jia, Shaowu Xu, Yuhan Zhou, Luo Wang, Weiting Li

Published: 01 Jan 2023, Last Modified: 12 Nov 2025Pattern Recognit. Lett. 2023EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•The FACS-GCN is built to model the inherent AU relations referring to FACS.•The DLR-GCN is built to complement individual differences ignored by FACS-GCN.•The DGCN is proposed to integrate two types factors impacting AU recognition.•The proposed method performs well on CK+ and RAF-AU.