Skeleton Based Action Recognition On Florence
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Rolling Rotations (FTP) | 91.40% | Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data | - |
| Complete GR-GCN | 98.4% | Optimized Skeleton-based Action Recognition via Sparsified Graph Regression | - |
| SCK⊕+DCK⊕ | 97.45 | Tensor Representations for Action Recognition | - |
| Lie Group | 90.9% | Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group | |
| Temporal Spectral Clustering + Temporal Subspace Clustering | 95.81% | Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning | - |
| SCK+DCK | 95.23 | Tensor Representations for Action Recognition | - |
| Deep STGC_K | 99.1% | Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition | - |
0 of 7 row(s) selected.