@inproceedings{pandey-etal-2023-cross,
    title = "Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment",
    author = "Pandey, Rohan  and
      Shao, Rulin  and
      Liang, Paul Pu  and
      Salakhutdinov, Ruslan  and
      Morency, Louis-Philippe",
    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/jlcl-multiple-ingestion/2023.acl-long.298/",
    doi = "10.18653/v1/2023.acl-long.298",
    pages = "5444--5455"
}