@inproceedings{distillingvisionlanguagemodelsonmillions,
  title = {Distilling Vision-Language Models on Millions of Videos},
  author = {Yue Zhao and Long Zhao and Xingyi Zhou and Jialin Wu and Chun-Te Chu and Hui Miao and Florian Schroff and Hartwig Adam and Ting Liu and Boqing Gong and Philipp Krähenbühl and Liangzhe Yuan},
  year = {2024},
  booktitle = {CVPR 2024 1},
  eprint = {2401.06129},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.06129v2},
}