@misc{rizve2024vidla,
  title={VidLA: Video-Language Alignment at Scale},
  author={Mamshad Nayeem Rizve and Fan Fei and Jayakrishnan Unnikrishnan and Son Tran and Benjamin Z. Yao and Belinda Zeng and Mubarak Shah and Trishul Chilimbi},
  year={2024},
  eprint={2403.14870},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2403.14870}
}