@inproceedings{li-etal-2020-vmsmo,
    title = "{VMSMO}: Learning to Generate Multimodal Summary for Video-based News Articles",
    author = "Li, Mingzhe  and
      Chen, Xiuying  and
      Gao, Shen  and
      Chan, Zhangming  and
      Zhao, Dongyan  and
      Yan, Rui",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.emnlp-main.752/",
    doi = "10.18653/v1/2020.emnlp-main.752",
    pages = "9360--9369"
}