EventFormer: AU Event Transformer for Facial Action Unit Event Detection

Abstract

Facial action units (AUs) play an indispensable role in human emotion analysis. We observe that although AUbased high-level emotion analysis is urgently needed by realworld applications, frame-level AU results provided by previous works cannot be directly used for such analysis. Moreover, as AUs are dynamic processes, the utilization of global temporal information is important but has been gravely ignored in the literature. To this end, we propose EventFormer for AU event detection, which is the first work directly detecting AU events from a video sequence by viewing AU event detection as a multiple class-specific sets prediction problem. Extensive experiments conducted on a commonly used AU benchmark dataset, BP4D, show the superiority of EventFormer under suitable metrics.