Multi Person Pose Estimation On Posetrack2018
Metrics
Mean mAP
Results
Performance results of various models on this benchmark
Model Name | Mean mAP | Paper Title | Repository |
|---|---|---|---|
| Poseidon | 87.8 | Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion | |
| DCPose | 79 | Deep Dual Consecutive Network for Human Pose Estimation | |
| PoseWarper | 78 | Learning Temporal Pose Estimation from Sparsely-Labeled Videos | |
| Refine | 73.8 | Learning to Refine Human Pose Estimation | - |
0 of 4 row(s) selected.