UNIT: Unifying Image and Text Recognition in One Vision Encoder

@article{zhu2024unit,
  title = {UNIT: Unifying Image and Text Recognition in One Vision Encoder},
  author = {Yi Zhu and Yanpeng Zhou and Chun-Wei Wang and Yang Cao and Jianhua Han and Lu Hou and Hang Xu},
  year = {2024},
  journal = {Neural Information Processing Systems},
  eprint = {2409.04095},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.04095},
}