@inproceedings{han-etal-2022-ynu,
    title = "{YNU}-{HPCC} at {S}em{E}val-2022 Task 5: Multi-Modal and Multi-label Emotion Classification Based on {LXMERT}",
    author = "Han, Chao  and
      Wang, Jin  and
      Zhang, Xuejie",
    editor = "Emerson, Guy  and
      Schluter, Natalie  and
      Stanovsky, Gabriel  and
      Kumar, Ritesh  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      Singh, Siddharth  and
      Ratan, Shyam",
    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.semeval-1.104/",
    doi = "10.18653/v1/2022.semeval-1.104",
    pages = "748--755",
    abstract = "This paper describes our system used in the SemEval-2022 Task5 Multimedia Automatic Misogyny Identification (MAMI). This task is to use the provided text-image pairs to classify emotions. In this paper, We propose a multi-label emotion classification model based on pre-trained LXMERT. We use Faster-RCNN to extract visual representation and utilize LXMERT`s cross-attention for multi-modal alignment. Then we use the Bilinear-interaction layer to fuse these features. Our experimental results surpass the $F_1$ score of baseline. For Sub-task A, our $F_1$ score is 0.662 and Sub-task B`s $F_1$ score is 0.633. The code of this study is available on GitHub."
}