Video Emotion Recognition On Crema D
Metrics
WAR
Results
Performance results of various models on this benchmark
Model Name | WAR | Paper Title | Repository |
|---|---|---|---|
| MultiMAE-DER | 79.36% | MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition | |
| MTCAE-DFER | - | MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition | |
| VAVL | - | Versatile audio-visual learning for emotion recognition | - |
0 of 3 row(s) selected.