Emotion Recognition In Conversation On Cmu 2
평가 지표
Accuracy
Weighted F1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Accuracy | Weighted F1 | Paper Title | Repository |
|---|---|---|---|---|
| MMGCN | 45.67 | 44.11 | MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation | |
| GraphSmile | 46.82 | 44.93 | Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition | |
| SACL-LSTM | 38.60 | 25.95 | Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations | |
| M3Net | 43.67 | 41.12 | Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation | - |
| COGMEN | - | 43.90 | COGMEN: COntextualized GNN based Multimodal Emotion recognitioN | |
| MM-DFN | 45.29 | 42.98 | MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations | |
| DialogueCRN | 37.88 | 26.55 | DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations |
0 of 7 row(s) selected.