@misc{multimodalityvinvl2021,
  title = {{VinVL: Revisiting Visual Representations in Vision-Language Models}},
  author = {Pengchuan Zhang and Xiujun Li and Xiaowei Hu and Jianwei Yang and Lei Zhang and Lijuan Wang and Yejin Choi and Jianfeng Gao},
  year = {2021},
  eprint = {2101.00529},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2101.00529v2}
}
