Keypoint Detection On Mpii Multi Person
Métriques
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Paper Title | Repository | |
|---|---|---|---|
| Associative Embedding | 77.5% | Associative Embedding: End-to-End Learning for Joint Detection and Grouping | - |
| AlphaPose | 82.1% | RMPE: Regional Multi-person Pose Estimation | - |
| Articulated Tracking | 74.3% | ArtTrack: Articulated Multi-person Tracking in the Wild | - |
| Local Joint-to-Person Association | 62.2% | Multi-Person Pose Estimation with Local Joint-to-Person Associations | - |
| Refine | 78% | Learning to Refine Human Pose Estimation | - |
| SPM | 78.5% | Single-Stage Multi-Person Pose Machines | - |
| Part Affinity Fields | 75.6% | Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields | - |
| Generative Partition Networks | 80.4% | Generative Partition Networks for Multi-Person Pose Estimation | - |
| DeeperCut | 59.4% | DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model | - |
0 of 9 row(s) selected.