Animal Pose Estimation On Ap 10K
Metrics
AP
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| ViTPose+-H | 82.4 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| ViTPose+-L | 80.4 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| SuperAnimal-HRNetw32 | 80.113 | SuperAnimal pretrained pose estimation models for behavioral analysis |
| UniPose | 79.2 | X-Pose: Detecting Any Keypoints |
| ViTPose+-B | 74.5 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| HRNet-w48 | 73.1 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| HRNet-w32 | 72.2 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| ViTPose+-S ViT-S | 71.4 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| SimpleBaseline-ResNet50 | 68.1 | ViTPose++: Vision Transformer for Generic Body Pose Estimation |
| zero-shot SuperAnimal-HRNetw32 | 68.038 | SuperAnimal pretrained pose estimation models for behavioral analysis |
0 of 10 row(s) selected.