@misc{multimodalityvilla2020,
  title = {{Large-Scale Adversarial Training for Vision-and-Language Representation Learning}},
  author = {Zhe Gan and Yen-Chun Chen and Linjie Li and Chen Zhu and Yu Cheng and Jingjing Liu},
  year = {2020},
  eprint = {2006.06195},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2006.06195}
}
