@inproceedings{liu-etal-2024-semantics,
    title = "Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training",
    author = "Liu, Haowei  and
      Shi, Yaya  and
      Xu, Haiyang  and
      Yuan, Chunfeng  and
      Ye, Qinghao  and
      Li, Chenliang  and
      Yan, Ming  and
      Zhang, Ji  and
      Huang, Fei  and
      Li, Bing  and
      Hu, Weiming",
    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://preview.aclanthology.org/fix-sig-urls/2024.lrec-main.1277/",
    pages = "14664--14675"
}