| Paper | Code | Top-1 Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition | 97.0 | PeVL ViT-L/14 | 2024-06-17 | |
| SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition | ✓ Link | 96.5 | SkeletonAgent | 2025-11-27 |
| Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition | ✓ Link | 95.9 | ProtoGCN | 2024-11-28 |
| PYSKL: Towards Good Practices for Skeleton Action Recognition | ✓ Link | 94.1 | PYSKL | 2022-05-19 |
| VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention | ✓ Link | 92.8 | VA-AR | 2025-03-14 |