Pose Estimation On Leeds Sports Poses
Metrics
PCK
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | PCK |
|---|---|
| human-pose-estimation-via-convolutional-part | 90.7% |
| jointly-optimize-data-augmentation-and | 94.5% |
| unipose-unified-human-pose-estimation-in | 94.5% |
| toward-fast-and-accurate-human-pose | 94.8% |
| convolutional-pose-machines | 90.5% |
| omnipose-a-multi-scale-framework-for-multi | 99.5% |
| monocular-3d-human-pose-estimation-in-the | 75.7 |
| human-pose-regression-by-combining-indirect | 90.5% |
| learning-feature-pyramids-for-human-pose | 93.9% |
| articulated-pose-estimation-by-a-graphical | 73.4% |
| multi-context-attention-for-human-pose | 92.6% |
| deepercut-a-deeper-stronger-and-faster-multi | 90.1% |
| self-adversarial-training-for-human-pose | 94% |
| learning-dynamical-human-joint-affinity-for | 87.5% |
| knowledge-guided-deep-fractal-neural-networks | 93.9% |
| vnect-real-time-3d-human-pose-estimation-with | 79.4 |
| trajectory-space-factorization-for-deep-video | 83.6 |
| fast-human-pose-estimation | 90.8% |