English

MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation

Computer Vision and Pattern Recognition 2014-09-30 v1 Machine Learning Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@article{arxiv.1409.7963,
  title  = {MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation},
  author = {Arjun Jain and Jonathan Tompson and Yann LeCun and Christoph Bregler},
  journal= {arXiv preprint arXiv:1409.7963},
  year   = {2014}
}
R2 v1 2026-06-22T06:07:52.461Z