@inproceedings{wang-etal-2022-understanding-multimodal,
    title = "Understanding {ME}? Multimodal Evaluation for Fine-grained Visual Commonsense",
    author = "Wang, Zhecan  and
      You, Haoxuan  and
      He, Yicheng  and
      Li, Wenhao  and
      Chang, Kai-Wei  and
      Chang, Shih-Fu",
    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/Add-Cong-Liu-Florida-Atlantic-University-author-id/2022.emnlp-main.626/",
    doi = "10.18653/v1/2022.emnlp-main.626",
    pages = "9212--9224"
}