Multi-Task Learning for Emotion Descriptors Estimation at the fourth ABAW Challenge
This work addresses performance issues in facial affective analysis for applications in the wild, but it appears incremental as it builds on existing multi-task learning approaches without claiming major breakthroughs.
The paper tackled the problem of limited performance in facial affective analysis tasks (valence/arousal, expression, and action unit estimation) in the wild by introducing a multi-task learning framework with feature sharing and label fusion, achieving unspecified results as no concrete numbers were provided.
Facial valence/arousal, expression and action unit are related tasks in facial affective analysis. However, the tasks only have limited performance in the wild due to the various collected conditions. The 4th competition on affective behavior analysis in the wild (ABAW) provided images with valence/arousal, expression and action unit labels. In this paper, we introduce multi-task learning framework to enhance the performance of three related tasks in the wild. Feature sharing and label fusion are used to utilize their relations. We conduct experiments on the provided training and validating data.