MoVi

MoVi is the first human motion dataset to contain synchronized pose, body meshes and video recordings. The MoVi database can be applied in human pose estimation and tracking, human motion prediction and synthesis, action recognition and gait analysis. For more information visit the main website

Publication

Here is a link to the PLOS ONE manuscript.

Code

The code containing the model and tutorial is hosted on GitHub which can be found here.

Referencing the MoVi Dataset

@article{ghorbani2021movi,
  title={MoVi: A large multi-purpose human motion and video dataset},
  author={Ghorbani, Saeed and Mahdaviani, Kimia and Thaler, Anne and Kording, Konrad and Cook, Douglas James and Blohm, Gunnar and Troje, Nikolaus F},
  journal={Plos one},
  volume={16},
  number={6},
  pages={e0253157},
  year={2021},
  publisher={Public Library of Science San Francisco, CA USA}
}