| Paper | Code | Accuracy | WAR | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection | ✓ Link | 85.68% | VAEmo | 2025-05-05 | |
| MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition | ✓ Link | 85.03% | MTCAE-DFER | 2024-12-25 | |
| Versatile audio-visual learning for emotion recognition | 82.60% | VAVL | 2023-05-12 | ||
| MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition | ✓ Link | 79.36% | MultiMAE-DER | 2024-04-28 |