@article{rositaenhancingvisionandlanguagesemantic,
  title = {ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration},
  author = {Yuhao Cui and Zhou Yu and Chunqi Wang and Zhongzhou Zhao and Ji Zhang and Meng Wang and Jun Yu},
  year = {2021},
  eprint = {2108.07073},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2108.07073v1},
}