Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks

@article{Wang2016ActionRB,
  title={Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks},
  author={Pichao Wang and Wanqing Li and Chuankun Li and Yonghong Hou},
  journal={CoRR},
  year={2016},
  volume={abs/1612.09401}
}
Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvNets to sequence-based data is still an open problem. This paper proposes an effective yet simple method to represent spatio-temporal information carried in 3D skeleton sequences into three 2D images by encoding the joint trajectories and their dynamics into color distribution in the images, referred to as Joint… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 16 times over the past 90 days. VIEW TWEETS