@inproceedings{jiangkuo-etal-2024-chinese,
    title = "{C}hinese Vision-Language Understanding Evaluation",
    author = "Jiangkuo, Wang  and
      Linwei, Zheng  and
      Kehai, Chen  and
      Xuefeng, Bai  and
      Min, Zhang",
    editor = "Lin, Hongfei  and
      Tan, Hongye  and
      Li, Bin",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.ccl-3.41/",
    pages = "363--373",
    language = "eng",
    abstract = "{\textquotedblleft}This paper introduces our systems submitted for the Chinese Vision-Language Understanding Evaluation task at the 23rd Chinese Computational Linguistics Conference.In this competition, we utilized X2-VLM and CCLM models to participate in various subtasks such as image-text retrieval, visual grounding, visual dialogue, and visual question answering. Additionally, we employed other models to assess performance on certain subtasks. We optimized our models and successfully applied them to these different tasks{\textquotedblright}"
}