Multimodal Emotion Recognition on CMU-MOSEI
76.81AccuracySegment Level Attention + Bi-Modal Transformer
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Segment Level Attention + Bi-Modal Transformer2026.05 | 76.81 | — | — | |
| Memory Bear AI2026.03 | 66.7 | 45.8 | 42.3 | |
| MulTDescription=Strong neural multimodal baseline2026.03 | 65.4 | 45.2 | 41.8 | |
| EmoEmbsDescription=Context-/emotion-aware baseline2026.03 | 64.2 | 44.2 | 40.8 | |
| LF-LSTMDescription=Traditional fusion baseline2026.03 | 63.1 | 43.3 | 39.5 |