Audio motion dataset

Visit the project webpage.

This dataset is composed of paired motion sequences from different characters and annotated motion retargeting constraints. For each video sequence, we provide a refined 3D actor reconstructed motion and the actor body shape estimated with Alldieck et al. (2018).

Citation

@article{ferreira2021cag,
  author={João P. Ferreira and Thiago M. Coutinho and Thiago L. Gomes and José F. Neto and Rafael Azevedo and Renato Martins and Erickson R. Nascimento},
  title = {Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio},
  journal = {Computers & Graphics}
  volume = {94},
  pages = {11 - 21},
  year={2021},
  issn={0097-8493}
  doi={https://doi.org/10.1016/j.cag.2020.09.009}
}

Data info

The Table below shows the number of samples in the dataset.

number of samples in the dataset

Copyright Notice

This dataset is published under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License. This means you must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. You may not use the material for commercial purposes.

Downloads

Downloading all data

Please take a look at the script dataset_tools/download_data.sh in our github repository https://github.com/verlab/Learning2Dance_CAG_2020

Downloading separately the data

Download our training dataset split at the link: https://www.verlab.dcc.ufmg.br/l2d/datasets/l2d_train.tar.gz
You can download our evaluation dataset split at the link: https://www.verlab.dcc.ufmg.br/l2d/datasets/l2d_eval.tar.gz
The url to the videos for training the audio classifier are at the link: https://www.verlab.dcc.ufmg.br/l2d/datasets/l2d_audios.zip

Alternative download

Alternatively you can download our datasets using the link: https://drive.google.com/drive/folders/12h6f5Y_Qxq5U40hBUuUCLltrSLONiXin?usp=sharing