Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

Abstract

Deep ConvNets have been shown to be effective for the task of human pose estimation from single images. However, several challenging issues arise in the video-based case such as self-occlusion, motion blur, and uncommon poses with few or no examples in training data sets. Temporal information can provide additional cues about the location of body joints and help to alleviate these issues. In this paper, we propose a deep structured model to estimate a sequence of human poses in unconstrained videos. This model can be efficiently trained in an end-to-end manner and is capable of representing appearance of body joints and their spatio-temporal relationships simultaneously. Domain knowledge about the human body is explicitly incorporated into the network providing effective priors to regularize the skeletal structure and to enforce temporal consistency. The proposed end-to-end architecture is evaluated on two widely used benchmarks (Penn Action dataset and JHMDB dataset) for video-based pose estimation. Our approach significantly outperforms the existing state-of-the-art methods.

Preliminary version to appear in CVPR2017

References in corpus (7)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• Stacked Hourglass Networks for Human Pose Estimation
• Convolutional Pose Machines
• Flowing ConvNets for Human Pose Estimation in Videos
• DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
• MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
• Chained Predictions Using Convolutional Neural Networks

Cited by in corpus (3)

• Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
• Learning to Refine Human Pose Estimation
• KFNet: Learning Temporal Camera Relocalization using Kalman Filtering