@article{visionlanguagemodelbasedcaption,
  title = {Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction},
  author = {Koki Maeda and Shuhei Kurita and Taiki Miyanishi and Naoaki Okazaki},
  year = {2024},
  eprint = {2402.17969},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.17969v1},
}