CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark

CVPR 2019 Jiefeng LiCan WangHao ZhuYihuan MaoHao-Shu FangCewu Lu

Multi-person pose estimation is fundamental to many computer vision tasks and has made significant progress in recent years. However, few previous methods explored the problem of pose estimation in crowded scenes while it remains challenging and inevitable in many scenarios... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Multi-Person Pose Estimation CrowdPose Joint-candidate SPPE + mAP @0.5:0.95 66.0 # 2
AP Easy 75.5 # 2
AP Medium 66.3 # 3
AP Hard 57.4 # 2
FPS 10.1 # 1