@inproceedings{TEMOS:2022,
  title = {{TEMOS}: Generating Diverse Human Motions from Textual Descriptions},
  aword_paper = {Oral},
  booktitle = {European Conference on Computer Vision (ECCV 2022)},
  abstract = {We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generating plausible and realistic sequences of human poses. In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data, in combination with a text encoder that produces distribution parameters compatible with the VAE latent space. We show the TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions. We evaluate our approach on the KIT Motion-Language benchmark and, despite being relatively straightforward, demonstrate significant improvements over the state of the art. Code and models are available on our webpage.},
  publisher = {Springer International Publishing},
  month = oct,
  year = {2022},
  slug = {temos-2022},
  author = {Petrovich, Mathis and Black, Michael J. and Varol, G\"{u}l},
  url = {https://mathis.petrovich.fr/temos},
  month_numeric = {10}
}