@inproceedings{svitttemporallearningofsparsevideotext,
  title = {SViTT: Temporal Learning of Sparse Video-Text Transformers},
  author = {Yi Li and Kyle Min and Subarna Tripathi and Nuno Vasconcelos},
  year = {2023},
  booktitle = {CVPR 2023 1},
  eprint = {2304.08809},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2304.08809v1},
}