Multi-person pose estimation on PoseTrack Challenge (val)
81.7Head mAPSimple Baseline (Ours)
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Simple Baseline (Ours)Backbone=ResNet-152, Detector=FPN-DCN [10]2018.04 | 81.7 | 83.4 | 80 | 72.4 | 75.3 | 74.8 | 67.1 | 76.7 | |
| Simple Baseline (Ours)Backbone=ResNet-50, Detector=FPN-DCN [10]2018.04 | 79.1 | 80.5 | 75.5 | 66 | 70.8 | 70 | 61.7 | 72.4 | |
| Girdhar et al.2018.02 | 67.5 | 70.2 | 62 | 51.7 | 60.7 | 58.7 | 49.8 | 60.6 | |
| Girdhar et al.2018.04 | 67.5 | 70.2 | 62 | 51.7 | 60.7 | 58.7 | 49.8 | 60.6 | |
| Pose Flow2018.02 | 66.7 | 73.3 | 68.3 | 61.1 | 67.5 | 67 | 61.3 | 66.5 | |
| Xiu et al.2018.04 | 66.7 | 73.3 | 68.3 | 61.1 | 67.5 | 67 | 61.3 | 66.5 |