@misc{multimodalityalbef2021,
  title = {{Align before Fuse: Vision and Language Representation Learning with Momentum Distillation}},
  author = {Junnan Li and Ramprasaath R. Selvaraju and Akhilesh Deepak Gotmare and Shafiq Joty and Caiming Xiong and Steven Hoi},
  year = {2021},
  eprint = {2107.07651},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2107.07651}
}
