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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
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

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Pose Estimation MPII Human Pose Stacked Hourglass Networks PCKh-0.5 90.9% # 21

Methods used in the Paper


METHOD TYPE
Residual Connection
Skip Connections
Convolution
Convolutions
1x1 Convolution
Convolutions
ReLU
Activation Functions
Max Pooling
Pooling Operations
Step Decay
Learning Rate Schedules
RMSProp
Stochastic Optimization
Batch Normalization
Normalization
Hourglass Module
Image Model Blocks
Stacked Hourglass Network
Pose Estimation Models