MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
Arjun Jain, Jonathan Tompson, Yann LeCun, Christoph Bregler · arXiv (Cornell University) · 2014
In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features. We propose a new human body pose dataset, FLIC-motion, that extends the FLIC dataset with additional motion features. We apply our architecture to this dataset and report significantly better performance than current state-of-the-art pose detection systems.