@inproceedings{metapersonalizingvisionlanguagemodelsto1,
  title = {Meta-Personalizing Vision-Language Models to Find Named Instances in Video},
  author = {Chun-Hsiao Yeh and Bryan Russell and Josef Sivic and Fabian Caba Heilbron and Simon Jenni},
  year = {2023},
  booktitle = {CVPR 2023 1},
  eprint = {2306.10169},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.10169v1},
}