@inproceedings{zhu-etal-2025-read,
    title = "Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing",
    author = "Zhu, HaiXiang  and
      Su, Lixian  and
      Mao, ShuangMing  and
      Ye, Jing",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2025.coling-main.76/",
    pages = "1136--1149"
}