@inproceedings{sun-etal-2024-lightvlp,
    title = "{L}ight{VLP}: A Lightweight Vision-Language Pre-training via Gated Interactive Masked {A}uto{E}ncoders",
    author = "Sun, Xingwu  and
      Yang, Zhen  and
      Xie, Ruobing  and
      Lian, Fengzong  and
      Kang, Zhanhui  and
      Xu, Chengzhong",
    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/jlcl-multiple-ingestion/2024.lrec-main.918/",
    pages = "10499--10510"
}