@inproceedings{zhang-etal-2024-multi,
    title = "Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment",
    author = "Zhang, Ming  and
      Chang, Ke  and
      Wu, Yunfang",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.1042/",
    pages = "11934--11943"
}