DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model

10 May 2016Eldar InsafutdinovLeonid PishchulinBjoern AndresMykhaylo AndrilukaBernt Schiele

The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Pose Estimation Leeds Sports Poses ResNet-152 + intermediate supervision PCK 90.1% # 4
Pose Estimation MPII Human Pose ResNet-152 + intermediate supervision PCKh-0.5 88.52% # 11
Multi-Person Pose Estimation MPII Multi-Person DeeperCut AP 59.4% # 7
Multi-Person Pose Estimation WAF DeeperCut AOP 88.10% # 1