End-to-End Multi-Person Pose Estimation with Transformers

Open paper
Benchmark Model Rank Results
human-pose-keypoint-estimation-on-coco-test-devPETR (Swin-L, multi-scale)#59AP: 71.2AP50: 91.4AP75: 79.6
human-pose-keypoint-estimation-on-coco-test-devPETR (Swin-L)#69AP: 70.5AP50: 91.5AP75: 78.7

Rank counts only results with a code link.