Two-Aspect Information Fusion Model For ABAW4 Multi-task Challenge
This work addresses the challenge of multi-task emotion prediction in affective behavior analysis, but it appears incremental as it builds on existing approaches by focusing on interactions between descriptors.
The paper tackled the problem of predicting multiple emotion descriptors from videos in the ABAW4 competition by proposing a two-aspect information fusion model that integrates different types of information, achieving effective results as demonstrated experimentally.
In this paper, we propose the solution to the Multi-Task Learning (MTL) Challenge of the 4th Affective Behavior Analysis in-the-wild (ABAW) competition. The task of ABAW is to predict frame-level emotion descriptors from videos: discrete emotional state; valence and arousal; and action units. Although researchers have proposed several approaches and achieved promising results in ABAW, current works in this task rarely consider interactions between different emotion descriptors. To this end, we propose a novel end to end architecture to achieve full integration of different types of information. Experimental results demonstrate the effectiveness of our proposed solution.