BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation

Open paper
Benchmark Model Rank Results
human-pose-keypoint-estimation-on-coco-test-devBoIR (HRNet-W48)#60AP: 71.2AP50: 90.8AP75: 78.6AR: 77.1
human-pose-keypoint-estimation-on-coco-val2017BoIR (HRNet-W48)#73AP: 72.5AP50: 89.9AP75: 79.1AR: 78.3

Rank counts only results with a code link.