Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

Abstract

This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training of these two model paradigms improves performance and allows us to significantly outperform existing state-of-the-art techniques.

Cited by in corpus (5)

• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Learning Deep Structured Models
• Pose from Action: Unsupervised Learning of Pose Features based on Motion
• Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models
• Deep Markov Random Field for Image Modeling