@inproceedings{swinbertendtoendtransformerswithsparse,
  title = {SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning},
  author = {Kevin Lin and Linjie Li and Chung-Ching Lin and Faisal Ahmed and Zhe Gan and Zicheng Liu and Yumao Lu and Lijuan Wang},
  year = {2021},
  booktitle = {CVPR 2022 1},
  eprint = {2111.13196},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2111.13196v4},
}