@article{visionlanaugepretrainingbycontrastive,
  title = {Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation},
  author = {Chaoya Jiang and Wei Ye and Haiyang Xu and Miang yan and Shikun Zhang and Jie Zhang and Fei Huang},
  year = {2023},
  eprint = {2305.04474},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.04474v3},
}