@article{learningspatiotemporalfeatureswithtwo,
  title = {Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading},
  author = {Xinshuo Weng and Kris Kitani},
  year = {2019},
  eprint = {1905.02540},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1905.02540v2},
}