HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

Benchmark Model Rank Results
human-pose-keypoint-estimation-on-coco-test-devHigherHRNet (HR-Net-48)#68AP: 70.5AP50: 89.3AP75: 77.2
multi-person-pose-estimation-on-crowdposeHigherHRNet(HR-Net-48)#13mAP @0.5:0.95: 67.6AP Easy: 75.8AP Medium: 68.1AP Hard: 58.9