@inproceedings{qu-etal-2024-visually,
    title = "Visually-Aware Context Modeling for News Image Captioning",
    author = "Qu, Tingyu  and
      Tuytelaars, Tinne  and
      Moens, Marie-Francine",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.naacl-long.162/",
    doi = "10.18653/v1/2024.naacl-long.162",
    pages = "2927--2943"
}