ArtTrack: Articulated Multi-person Tracking in the Wild

CVPR 2017 Eldar InsafutdinovMykhaylo AndrilukaLeonid PishchulinSiyu TangEvgeny LevinkovBjoern AndresBernt Schiele

In this paper we propose an approach for articulated tracking of multiple people in unconstrained videos. Our starting point is a model that resembles existing architectures for single-frame pose estimation but is substantially faster... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Multi-Person Pose Estimation MPII Multi-Person Articulated Tracking AP 74.3% # 5