@article{efficientvisionandlanguagepretraining,
  title = {Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection},
  author = {Wei Ye and Chaoya Jiang and Haiyang Xu and Chenhao Ye and Chenliang Li and Ming Yan and Shikun Zhang and Songhang Huang and Fei Huang},
  year = {2024},
  eprint = {2403.07883},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.07883v1},
}