Learning to Refine Human Pose Estimation

Open paper
Benchmark Model Rank Results
keypoint-detection-on-mpii-multi-personRefine–mAP@0.5: 78%
multi-person-pose-estimation-on-mpii-multiRefine–AP: 78%
multi-person-pose-estimation-on-posetrack2018Refine–Mean mAP: 73.8

Rank counts only results with a code link.