DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

CVPR 2016 Leonid PishchulinEldar InsafutdinovSiyu TangBjoern AndresMykhaylo AndrilukaPeter GehlerBernt Schiele

This paper considers the task of articulated human pose estimation of multiple people in real world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Pose Estimation MPII Human Pose DeepCut PCKh-0.5 82.40% # 14
Multi-Person Pose Estimation WAF DeepCut AOP 86.5% # 2