@article{multimodalunderstandingandgenerationfor,
  title = {Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training},
  author = {Jong Hak Moon and Hyungyung Lee and Woncheol Shin and Young-Hak Kim and Edward Choi},
  year = {2021},
  eprint = {2105.11333},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2105.11333v3},
}