@inproceedings{thapliyal-etal-2022-crossmodal,
    title = "Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset",
    author = "Thapliyal, Ashish V.  and
      Pont Tuset, Jordi  and
      Chen, Xi  and
      Soricut, Radu",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.emnlp-main.45/",
    doi = "10.18653/v1/2022.emnlp-main.45",
    pages = "715--729"
}