@inproceedings{gupta-etal-2026-beyond,
    title = "Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules",
    author = "Gupta, Kishor Datta  and
      Haque, Mohd Ariful  and
      Kamal, Marufa  and
      Hasan, Ahmed Rafi  and
      Rahman, Md. Mahfuzur  and
      George, Roy",
    editor = "Yan, Qianqi  and
      Montariol, Syrielle  and
      Fan, Yue  and
      Gu, Jing  and
      Pan, Jiayi  and
      Li, Manling  and
      Kordjamshidi, Parisa  and
      Suhr, Alane  and
      Wang, Xin Eric",
    booktitle = "Proceedings of the 4th Workshop on Advances in Language and Vision Research ({ALVR})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.alvr-main.16/",
    pages = "199--208",
    ISBN = "979-8-89176-398-2"
}