Human Reaction Intensity Estimation with Ensemble of Multi-task Networks

2023/03/16 by Jiyeon Oh, Oh, JiYeon, Daun Kim +7
Psychology · #Emotion and Mood Recognition #Mental Health Research Topics #Digital Mental Health Interventions

paper · pdf · doi:10.48550/arxiv.2303.09240

Abstract

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.

Related

• Emotional Reaction Intensity Estimation Based on Multimodal Data
• Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networks
• Computer Vision Estimation of Emotion Reaction Intensity in the Wild
• An Ensemble Approach for Multiple Emotion Descriptors Estimation Using Multi-task Learning
• A Dual Branch Network for Emotional Reaction Intensity Estimation