@inproceedings{xu-etal-2024-mind,
    title = "{MIND}: Multimodal Shopping Intention Distillation from Large Vision-language Models for {E}-commerce Purchase Understanding",
    author = "Xu, Baixuan  and
      Wang, Weiqi  and
      Shi, Haochen  and
      Ding, Wenxuan  and
      Jing, Huihao  and
      Fang, Tianqing  and
      Bai, Jiaxin  and
      Liu, Xin  and
      Yu, Changlong  and
      Li, Zheng  and
      Luo, Chen  and
      Yin, Qingyu  and
      Yin, Bing  and
      Chen, Long  and
      Song, Yangqiu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2024.emnlp-main.446/",
    doi = "10.18653/v1/2024.emnlp-main.446",
    pages = "7800--7815"
}