@misc{multimodalityvilbert2019,
  title = {{ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks}},
  author = {Jiasen Lu and Dhruv Batra and Devi Parikh and Stefan Lee},
  year = {2019},
  eprint = {1908.02265},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.02265}
}
