@misc{multimodalitylxmert2019,
  title = {{LXMERT: Learning Cross-Modality Encoder Representations from Transformers}},
  author = {Hao Tan and Mohit Bansal},
  year = {2019},
  eprint = {1908.07490},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.07490}
}
