@inproceedings{chen-etal-2026-scenes,
    title = "From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal {RAG}",
    author = "Chen, Guanhua  and
      Huang, Chuyue  and
      Yao, Yutong  and
      Liu, Shudong  and
      Song, Xueqing  and
      Chao, Lidia S.  and
      Wong, Derek F.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.509/",
    pages = "10475--10491",
    ISBN = "979-8-89176-395-1"
}