@misc{visiontransformersbeitv22022,
  title = {{BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers}},
  author = {Zhiliang Peng and Li Dong and Hangbo Bao and Qixiang Ye and Furu Wei},
  year = {2022},
  eprint = {2208.06366},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2208.06366}
}
