@inproceedings{yao-etal-2022-pevl,
    title = "{PEVL}: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models",
    author = "Yao, Yuan  and
      Chen, Qianyu  and
      Zhang, Ao  and
      Ji, Wei  and
      Liu, Zhiyuan  and
      Chua, Tat-Seng  and
      Sun, Maosong",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.emnlp-main.763/",
    doi = "10.18653/v1/2022.emnlp-main.763",
    pages = "11104--11117"
}