Stacked Hourglass Networks for Human Pose Estimation

22 Mar 2016Alejandro NewellKaiyu YangJia Deng

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Pose Estimation FLIC Elbows Stacked Hourglass Networks [email protected] 99.0% # 1
Pose Estimation FLIC Wrists Stacked Hourglass Networks PCK[email protected] 97.0% # 1
Pose Estimation MPII Human Pose Stacked Hourglass Networks PCKh-0.5 90.9% # 9