TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection

arXiv:2403.04789v1 Announce Type: cross
Abstract: Multimodal Conversational Emotion (MCE) detection, generally spanning across the acoustic, vision and language modalities, has attracted increasing interest in the multimedia community. Previous studies predominantly focus on learning contextual information in conversations with only a few considering the topic information in single language modality, while always neglecting the acoustic and vision topic information. On this basis, we propose a model-agnostic Topic-enriched Diffusion (TopicDiff) approach for capturing multimodal topic information in MCE tasks. Particularly, we integrate …

abstract arxiv community conversational conversations cs.ai cs.cl cs.lg detection diffusion emotion emotion detection focus information language multimedia multimodal studies type vision