| Joint Pair | Angle (deg) | Kinematic Significance | |------------|-------------|------------------------| | Shoulder-Elbow-Wrist (R) | 142° | Near-extension, reaching upward-right | | Shoulder-Elbow-Wrist (L) | 88° (occluded) | Flexed, hidden behind back | | Hip-Knee-Ankle (R) | 165° | Almost straight, weight-bearing | | Hip-Knee-Ankle (L) | 112° | Flexed, possibly lifted | | Neck-Shoulder (R/L) | 25° / -12° | Asymmetrical shoulder elevation |
The performance gap illustrates progress in handling self-occlusion and non-frontal views. Notably, Pose 22 is often included in ablation studies as a "hard example" due to its [2]. 5. Cross-Dataset Comparison: The Ambiguity of "Pose 22" Outside MPII, "Pose 22" appears in other datasets with entirely different meanings: pose 22
[2] Newell, A., Yang, K., & Deng, J. (2016). Stacked Hourglass Networks for Human Pose Estimation. ECCV . | Joint Pair | Angle (deg) | Kinematic
| Model | PCKh@0.5 (score) | Failure mode | |-------|----------------|--------------| | OpenPose (2017) | 0.68 | Left wrist hallucinated in empty space | | HRNet-W32 (2019) | 0.85 | Correct left wrist location but low confidence | | ViTPose (2022) | 0.92 | All keypoints within 10px of ground truth | Cross-Dataset Comparison: The Ambiguity of "Pose 22" Outside