Pose Estimation On Coco Test Dev
Metrics
AP
AP50
AP75
APL
APM
AR
Results
Performance results of various models on this benchmark
Model Name | AP | AP50 | AP75 | APL | APM | AR | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| Flow-based (ResNet-152) | 73.7 | 91.9 | 81.1 | 80 | 70.3 | 79 | - | - |
| Mask-RCNN | 63.1 | 87.3 | 68.7 | 71.4 | - | - | - | - |
| PPE (ResNeXt-101) | 75.7 | 90.3 | 76.3 | 79.5 | 80.7 | - | - | - |
| OmniPose (WASPv2) | 76.4 | 92.6 | 83.7 | 82.6 | 72.6 | 81.2 | - | - |
| Faster R-CNN (ImageNet+300M) | 64.4 | 85.7 | 70.7 | 69.8 | 61.8 | - | - | - |
| Lite-HRNet-30 | 69.7 | 90.7 | 77.5 | 75.0 | 66.9 | 75.4 | - | - |
| MIPNet | 75.7 | 92.4 | 83.3 | 81.2 | 71.4 | 80.5 | - | - |
| TFPose (ND=6 ResNet-50) | 72.2 | 90.9 | 80.1 | 78.8 | 69.1 | - | - | - |
| PoseFix | 74.7 | 91.2 | 81.9 | 81.2 | 71.1 | 79.9 | - | - |
| MSPN | 76.1 | 93.4 | 83.8 | 81.5 | 72.3 | 81.6 | - | - |
| TransPose-H-A6 | 75 | 92.2 | 82.3 | 81.1 | 71.3 | - | - | - |
| HRNet-W48+UDP | 76.5 | 92.7 | 84 | 73.0 | 82.4 | 81.6 | - | - |
| HRNet-W48+DARK | 77.4 | 92.6 | 84.6 | 83.7 | 73.6 | 82.3 | - | - |
| CMU-Pose | 61.8 | 84.9 | 67.5 | 68.2 | 57.1 | 66.5 | - | - |
| ViTPose (ViTAE-G, ensemble) | 81.1 | 95.0 | 88.2 | 86.0 | 77.8 | 85.6 | - | - |
| ViTPose (ViTAE-G) | 80.9 | 94.8 | 88.1 | 85.9 | 77.5 | 85.4 | - | - |
| KAPAO-L | 70.3 | 91.2 | 77.8 | 76.8 | 66.3 | 77.7 | - | - |
| RMPE++ | 72.3 | 89.2 | 79.1 | 78.6 | 68.0 | - | - | - |
| CPN | 72.1 | 91.4 | 80.0 | 77.2 | - | 78.5 | - | - |
| yolopose | - | 90.3 | - | - | - | - | - | - |
0 of 46 row(s) selected.