@inproceedings{viltaenhancingvisionlanguagepretraining,
  title = {ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation},
  author = {Weihan Wang and Zhen Yang and Bin Xu and Juanzi Li and Yankui Sun},
  year = {2023},
  booktitle = {ICCV 2023 1},
  eprint = {2308.16689},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.16689v1},
}