@article{aprogressiveframeworkofvisionlanguage,
  title = {A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene},
  author = {Wenbo Zhang and Yifan Zhang and Jianfeng Lin and Binqiang Huang and Jinlu Zhang and Wenhao Yu},
  year = {2024},
  eprint = {2404.11249},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.11249v1},
}