@misc{li2022blip,
  title={BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
  author={Junnan Li and Dongxu Li and Caiming Xiong and Steven Hoi},
  year={2022},
  eprint={2201.12086},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2201.12086}
}