@inproceedings{zhang-etal-2022-cross,
    title = "Cross-Modal Similarity-Based Curriculum Learning for Image Captioning",
    author = "Zhang, Hongkuan  and
      Sugawara, Saku  and
      Aizawa, Akiko  and
      Zhou, Lei  and
      Sasano, Ryohei  and
      Takeda, Koichi",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.emnlp-main.516/",
    doi = "10.18653/v1/2022.emnlp-main.516",
    pages = "7599--7606"
}