ICML · 2023 · Conference paper

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

Ze-Jia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

Published in: International Conference on Machine Learning
Date: 2023-02-01
Citations: 86
arXiv: 2302.00624 ↗

Cite

@inproceedings{weng2023openvclip,
  title = {Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization},
  author = {Ze-Jia Weng and Xitong Yang and Ang Li and Zuxuan Wu and Yu-Gang Jiang},
  year = {2023},
  booktitle = {International Conference on Machine Learning},
  eprint = {2302.00624},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.00624},
}