TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Pose Estimation	FLIC Elbows	Stacked Hourglass Networks	PCK@0.2	99.0%	# 1
Pose Estimation	FLIC Wrists	Stacked Hourglass Networks	PCK@0.2	97.0%	# 1
Pose Estimation	MPII Human Pose	Stacked Hourglass Networks	PCKh-0.5	90.9	# 24

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/stacked-hourglass-networks-for-human-pose/pose-estimation-on-flic-elbows)](https://paperswithcode.com/sota/pose-estimation-on-flic-elbows?p=stacked-hourglass-networks-for-human-pose)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/stacked-hourglass-networks-for-human-pose/pose-estimation-on-flic-wrists)](https://paperswithcode.com/sota/pose-estimation-on-flic-wrists?p=stacked-hourglass-networks-for-human-pose)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/stacked-hourglass-networks-for-human-pose/pose-estimation-on-mpii-human-pose)](https://paperswithcode.com/sota/pose-estimation-on-mpii-human-pose?p=stacked-hourglass-networks-for-human-pose)`

Stacked Hourglass Networks for Human Pose Estimation

22 Mar 2016 · Alejandro Newell, Kaiyu Yang, Jia 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. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

PDF Abstract