@inproceedings{vidlavideolanguagealignmentatscale,
  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},
  booktitle = {CVPR 2024 1},
  eprint = {2403.14870},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.14870v1},
}