Problem
Research questions and friction points this paper is trying to address.
Multimodal Emotion Recognition
Conversational Context
Emotional Dynamics
Multimodal Emotion Recognition in Conversations via Class-Wise Adaptive Modality Fusion and Affective Geometry
🤖 AI Summary
本文通过结合面部几何特征、类别自适应模态融合和情感几何先验的方法，提高了对话中多模态情感识别的准确性。
📝 Abstract
Emotion Recognition in Conversations (ERC) requires integrating heterogeneous textual, audio, and visual cues while accounting for conversational context and emotional dynamics. We extend the Self-Distillation Transformer architecture for ERC with appearance+geometry visual representations, class-wise adaptive modality fusion, and a valence-arousal prior for affective transitions. On the MELD and IEMOCAP datasets, geometry-enhanced visual representations improve weighted F1 by 0.27 and 4.36 points over appearance-only features, respectively, while class-wise adaptive fusion provides further gains of 0.17 and 0.25 points over the original softmax gate. The valence-arousal prior yields targeted improvements of 0.30 and 0.74 accuracy points on emotionally shifted utterances while preserving performance on stable turns. These results indicate that structured facial cues, emotion-dependent modality weighting, and affective geometry provide complementary benefits for multimodal ERC.
Innovation
Methods, ideas, or system contributions that make the work stand out.
class-wise adaptive modality fusion
affective geometry
valence-arousal prior
🔎 Similar Papers
No similar papers found.
