@inproceedings{zhao-etal-2023-generating-visual,
    title = "Generating Visual Spatial Description via Holistic 3{D} Scene Understanding",
    author = "Zhao, Yu  and
      Fei, Hao  and
      Ji, Wei  and
      Wei, Jianguo  and
      Zhang, Meishan  and
      Zhang, Min  and
      Chua, Tat-Seng",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.acl-long.442/",
    doi = "10.18653/v1/2023.acl-long.442",
    pages = "7960--7977"
}