@inproceedings{yang2021tap,
  title={TAP: Text-Aware Pre-training for Text-VQA and Text-Caption},
  author={Yang, Zhengyuan and Lu, Yijuan and Wang, Jianfeng and Yin, Xi and Florencio, Dinei and Wang, Lijuan and Zhang, Cha and Zhang, Lei and Luo, Jiebo},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={8751--8761},
  year={2021}
}