Building an Open-Vocabulary Video CLIP Model With Better Architectures, Optimization and Data

@article{wu2023building,
  title = {Building an Open-Vocabulary Video CLIP Model With Better Architectures, Optimization and Data},
  author = {Zuxuan Wu and Ze-Jia Weng and Wujian Peng and Xitong Yang and Ang Li and Larry S Davis and Yu-Gang Jiang},
  year = {2023},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  eprint = {2310.05010},
  archivePrefix = {arXiv},
  doi = {10.1109/TPAMI.2024.3357503},
  url = {https://arxiv.org/abs/2310.05010},
}