@inproceedings{feiyu-etal-2024-bridging,
    title = "Bridging the Gap between Authentic and Answer-Guided Images for {C}hinese Vision-Language Understanding Enhancement",
    author = "Feiyu, Wang  and
      Wenyu, Guo  and
      Dong, Yu  and
      Chen, Kang  and
      Pengyuan, Liu",
    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-3.40/",
    pages = "353--362",
    language = "eng",
    abstract = "{\textquotedblleft}The objective of the Chinese Vision-Language Understanding Evaluation (CVLUE) is to comprehensively assess the performance of Chinese vision-language multimodal pre-trained models in multimodal modeling and understanding across four tasks: Image-Text Retrieval, Visual Question Answering, Visual Grounding, and Visual Dialog. To enhance the models' performance across various multimodal tasks, this paper propose a multimodal information understanding enhancement method based on answer-guided images. Firstly, we propose task-specific methods for answer-guided image generation. Secondly, the authentic and answer-guided images are fed into the model for multimodal fine-tuning, respectively. Finally, training objectives are set for different tasks to minimize the gap between the answer-guided images and authentic images, thereby supervising the results produced by the authentic images utlizing answer-guided images. The experimental results demonstrate the effectiveness of the proposed method.{\textquotedblright}"
}