Recurrent Network Models for Kinematic Tracking

  title={Recurrent Network Models for Kinematic Tracking},
  author={Katerina Fragkiadaki and Sergey Levine and Jitendra Malik},
We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. The ERD model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers. We test instantiations of ERD architectures in the tasks of motion capture (mocap) generation, body pose labeling and body pose forecasting in videos. Our model handles mocap training data across multiple subjects and activity… CONTINUE READING
11 Citations
52 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 52 references

Similar Papers

Loading similar papers…