@inproceedings{du-etal-2024-delan,
    title = "{DELAN}: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning",
    author = "Du, Mengfei  and
      Wu, Binhao  and
      Zhang, Jiwen  and
      Fan, Zhihao  and
      Li, Zejun  and
      Luo, Ruipu  and
      Huang, Xuanjing  and
      Wei, Zhongyu",
    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.411/",
    pages = "4605--4616"
}