TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection
This work addresses multimodal conversational emotion detection for the multimedia community, offering an incremental advance by integrating diffusion models with neural topic models to better capture topic information.
The paper tackled multimodal conversational emotion detection by proposing TopicDiff, a topic-enriched diffusion approach to capture multimodal topic information across acoustic, vision, and language modalities, resulting in significant improvements over state-of-the-art baselines.
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 the diffusion model into neural topic model to alleviate the diversity deficiency problem of neural topic model in capturing topic information. Detailed evaluations demonstrate the significant improvements of TopicDiff over the state-of-the-art MCE baselines, justifying the importance of multimodal topic information to MCE and the effectiveness of TopicDiff in capturing such information. Furthermore, we observe an interesting finding that the topic information in acoustic and vision is more discriminative and robust compared to the language.