@inproceedings{weaklysupervisedvisualbertpretraining,
  title = {Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions},
  author = {Liunian Harold Li and Haoxuan You and Zhecan Wang and Alireza Zareian and Shih-Fu Chang and Kai-Wei Chang},
  year = {2020},
  booktitle = {NAACL 2021 4},
  eprint = {2010.12831},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2010.12831v2},
}