@article{captionanythinginteractiveimage,
  title = {Caption Anything: Interactive Image Description with Diverse Multimodal Controls},
  author = {Teng Wang and Jinrui Zhang and Junjie Fei and Hao Zheng and Yunlong Tang and Zhe Li and Mingqi Gao and Shanshan Zhao},
  year = {2023},
  eprint = {2305.02677},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.02677v3},
}