Foundation Models for Video Understanding: A Survey

@misc{moeslund2024foundationmodelsvideo,
      title={Foundation Models for Video Understanding: A Survey}, 
      author={Thomas B. Moeslund and Yogesh S. Rawat and Rajat Modi and Neelu Madan and Andreas Moegelmose},
      year={2024},
      eprint={2405.03770},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2405.03770}, 
}