A Dual Branch Network for Emotional Reaction Intensity Estimation
This work addresses emotional reaction intensity estimation for applications in medicine and safe driving, but appears incremental as it builds on existing multimodal fusion techniques.
The paper tackles the problem of estimating emotional reaction intensity in multimodal scenarios by proposing a dual-branch multi-output regression model, achieving excellent results on the official validation set of the ABAW challenge.
Emotional Reaction Intensity(ERI) estimation is an important task in multimodal scenarios, and has fundamental applications in medicine, safe driving and other fields. In this paper, we propose a solution to the ERI challenge of the fifth Affective Behavior Analysis in-the-wild(ABAW), a dual-branch based multi-output regression model. The spatial attention is used to better extract visual features, and the Mel-Frequency Cepstral Coefficients technology extracts acoustic features, and a method named modality dropout is added to fusion multimodal features. Our method achieves excellent results on the official validation set.