Human Pose Estimation with Spatial Contextual Information

Abstract

We explore the importance of spatial contextual information in human pose estimation. Most state-of-the-art pose networks are trained in a multi-stage manner and produce several auxiliary predictions for deep supervision. With this principle, we present two conceptually simple and yet computational efficient modules, namely Cascade Prediction Fusion (CPF) and Pose Graph Neural Network (PGNN), to exploit underlying contextual information. Cascade prediction fusion accumulates prediction maps from previous stages to extract informative signals. The resulting maps also function as a prior to guide prediction at following stages. To promote spatial correlation among joints, our PGNN learns a structured representation of human pose as a graph. Direct message passing between different joints is enabled and spatial relation is captured. These two modules require very limited computational complexity. Experimental results demonstrate that our method consistently outperforms previous methods on MPII and LSP benchmark.

References in corpus (5)

• Semi-Supervised Classification with Graph Convolutional Networks
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Self Adversarial Training for Human Pose Estimation
• CRF-CNN: Modeling Structured Information in Human Pose Estimation
• An Expressive Deep Model for Human Action Parsing from A Single Image

Cited by in corpus (4)

• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Cascade Feature Aggregation for Human Pose Estimation
• Global Context for Convolutional Pose Machines
• Anti-Confusing: Region-Aware Network for Human Pose Estimation