@inproceedings{li-etal-2024-topviewrs,
    title = "{T}op{V}iew{RS}: Vision-Language Models as Top-View Spatial Reasoners",
    author = "Li, Chengzu  and
      Zhang, Caiqi  and
      Zhou, Han  and
      Collier, Nigel  and
      Korhonen, Anna  and
      Vuli{\'c}, Ivan",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.106/",
    doi = "10.18653/v1/2024.emnlp-main.106",
    pages = "1786--1807"
}