Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion

arXiv:2404.17858v1 Announce Type: new
Abstract: Multi-modal Emotion Recognition in Conversation (MERC) has received considerable attention in various fields, e.g., human-computer interaction and recommendation systems. Most existing works perform feature disentanglement and fusion to extract emotional contextual information from multi-modal features and emotion classification. After revisiting the characteristic of MERC, we argue that long-range contextual semantic information should be extracted in the feature disentanglement stage and the inter-modal semantic information consistency should be maximized in the feature fusion stage. Inspired by …

abstract arxiv attention classification computer conversation cs.cl emotion extract feature features fields fusion guidance human human-computer interaction information modal multi-modal probability recognition recommendation recommendation systems space state state space models systems type