@article{cocobertimprovingvideolanguagepre,
  title = {CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising},
  author = {Jianjie Luo and Yehao Li and Yingwei Pan and Ting Yao and Hongyang Chao and Tao Mei},
  year = {2021},
  eprint = {2112.07515},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.07515v1},
}