@inproceedings{ignat-etal-2021-whyact,
    title = "{W}hy{A}ct: Identifying Action Reasons in Lifestyle Vlogs",
    author = "Ignat, Oana  and
      Castro, Santiago  and
      Miao, Hanwen  and
      Li, Weiji  and
      Mihalcea, Rada",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2021.emnlp-main.392/",
    doi = "10.18653/v1/2021.emnlp-main.392",
    pages = "4770--4785",
    abstract = "We aim to automatically identify human action reasons in online videos. We focus on the widespread genre of lifestyle vlogs, in which people perform actions while verbally describing them. We introduce and make publicly available the WhyAct dataset, consisting of 1,077 visual actions manually annotated with their reasons. We describe a multimodal model that leverages visual and textual information to automatically infer the reasons corresponding to an action presented in the video."
}