@article{contrastivecrossmodalknowledgesharingpre,
  title = {Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval},
  author = {Keyu Wen and Zhenshan Tan and Qingrong Cheng and Cheng Chen and Xiaodong Gu},
  year = {2022},
  eprint = {2207.00733},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2207.00733v2},
}