@article{tag2textguidingvisionlanguagemodelvia,
  title = {Tag2Text: Guiding Vision-Language Model via Image Tagging},
  author = {Xinyu Huang and Youcai Zhang and Jinyu Ma and Weiwei Tian and Rui Feng and Yuejie Zhang and Yaqian Li and Yandong Guo and Lei Zhang},
  year = {2023},
  eprint = {2303.05657},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2303.05657v3},
}