2D Human Pose Estimation On Ochuman
Metrics
Test AP
Validation AP
Results
Performance results of various models on this benchmark
Model Name | Test AP | Validation AP | Paper Title | Repository |
|---|---|---|---|---|
| HRNet-W48 | 37.2 | 37.8 | Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation | |
| SEFD | 44.1 | - | SEFD: Learning to Distill Complex Pose and Occlusion | |
| Associative Embedding+ | 32.8 | 40.0 | Associative Embedding: End-to-End Learning for Joint Detection and Grouping | |
| ResNet-152 | 33.3 | 41.0 | Simple Baselines for Human Pose Estimation and Tracking | |
| MIPNet (HRNet-W48) | 42.5 | 42.0 | Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation | |
| Pose2Seg | 23.8 | - | Pose2Seg: Detection Free Human Instance Segmentation | |
| HGG (AE+) | 36.0 | 41.8 | Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation | - |
| BBox-Mask-Pose 2x | 48.3 | 48.6 | Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle | |
| Associative Embedding | 29.5 | 32.1 | Associative Embedding: End-to-End Learning for Joint Detection and Grouping | |
| ResNet-50 | 30.4 | 37.8 | Simple Baselines for Human Pose Estimation and Tracking | |
| RMPE | 30.7 | 38.8 | RMPE: Regional Multi-person Pose Estimation |
0 of 11 row(s) selected.