Human Pose Estimation for Real-World Crowded Scenarios
Open paper
Benchmark
Model
Rank
Results
multi-person-pose-estimation-on-crowdpose
OccNet
#16
mAP @0.5:0.95: 65.5
AP Easy: 75.2
AP Medium: 66.6
AP Hard: 53.1
Rank counts only results with a code link.