Convolutional Pose Machines

CVPR 2016 Shih-En WeiVarun RamakrishnaTakeo KanadeYaser Sheikh

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Pose Estimation FLIC Elbows Convolutional Pose Machines [email protected] 97.59% # 2
Pose Estimation FLIC Wrists Convolutional Pose Machines [email protected] 95.03% # 2
Pose Estimation Leeds Sports Poses Convolutional Pose Machines PCK 90.5% # 5
Pose Estimation MPII Human Pose Convolutional Pose Machines PCKh-0.5 88.52% # 13
3D Human Pose Estimation Total Capture Tri-CPM Average MPJPE (mm) 99 # 5