Human Reaction Intensity Estimation with Ensemble of Multi-task Networks
This work addresses the challenge of emotional reaction intensity estimation for interactive computing domains, but it appears incremental as it builds on existing competition frameworks.
The paper tackled the problem of estimating emotional reaction intensity from facial expressions in-the-wild, achieving a mean Pearson correlation coefficient (PCC) score of 0.3254 in the ABAW competition challenge.
Facial expression in-the-wild is essential for various interactive computing domains. Especially, "Emotional Reaction Intensity" (ERI) is an important topic in the facial expression recognition task. In this paper, we propose a multi-emotional task learning-based approach and present preliminary results for the ERI challenge introduced in the 5th affective behavior analysis in-the-wild (ABAW) competition. Our method achieved the mean PCC score of 0.3254.