@article{luan2024textcot,
  title={TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding},
  author={Luan, Bozhi and Feng, Hao and Chen, Hong and Wang, Yonghui and Zhou, Wengang and Li, Houqiang},
  journal={arXiv preprint arXiv:2404.09797},
  year={2024}
}