Can I read Knowledge-Aware Bayesian Co-Attention for Multimodal Emotion Recognition on EtoBox?

Knowledge-Aware Bayesian Co-Attention for Multimodal Emotion Recognition by Zihan Zhao; Yu Wang; Yanfeng Wang is a scholarly article available to read on EtoBox.

What is Knowledge-Aware Bayesian Co-Attention for Multimodal Emotion Recognition about?

Multimodal emotion recognition is a challenging research area that aims to fuse different modalities to predict human emotion. However, most existing models that are based on attention mechanisms have difficulty in learning emotionally relevant parts on their own. To solve this problem, we propose to incorporate external emotion-related knowledge in the co-attention based fusion of pre-trained models. To effectively incorporate this knowledge, we enhance the coattention model with a Bayesian attention module (BAM) where a prior distribution is estimated using the emotionrelated knowledge. Experimental results on the IEMOCAP dataset show that the proposed approach can outperform several state-of-the-art approaches by at least 0.7% unweighted accuracy (UA).

Author

Zihan Zhao; Yu Wang; Yanfeng Wang

Publisher

IEEE

Published

2023

Language

EN