@inproceedings{rethinkingvideovitssparsevideotubesfor,
  title = {Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning},
  author = {AJ Piergiovanni and Weicheng Kuo and Anelia Angelova},
  year = {2022},
  booktitle = {CVPR 2023 1},
  eprint = {2212.03229},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.03229v1},
}