@inproceedings{190807490v3,
  title = {LXMERT: Learning Cross-Modality Encoder Representations from Transformers},
  author = {Hao Tan and Mohit Bansal},
  year = {2019},
  booktitle = {IJCNLP 2019 11},
  eprint = {1908.07490},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.07490v3},
}