@inproceedings{liang-etal-2021-graghvqa,
    title = "{G}ragh{VQA}: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering",
    author = "Liang, Weixin  and
      Jiang, Yanhao  and
      Liu, Zixuan",
    editor = "Zadeh, Amir  and
      Morency, Louis-Philippe  and
      Liang, Paul Pu  and
      Ross, Candace  and
      Salakhutdinov, Ruslan  and
      Poria, Soujanya  and
      Cambria, Erik  and
      Shi, Kelly",
    booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.maiworkshop-1.12/",
    doi = "10.18653/v1/2021.maiworkshop-1.12",
    pages = "79--86",
    abstract = "Images are more than a collection of objects or attributes {---} they represent a web of relationships among interconnected objects. Scene Graph has emerged as a new modality as a structured graphical representation of images. Scene Graph encodes objects as nodes connected via pairwise relations as edges. To support question answering on scene graphs, we propose GraphVQA, a language-guided graph neural network framework that translates and executes a natural language question as multiple iterations of message passing among graph nodes. We explore the design space of GraphVQA framework, and discuss the trade-off of different design choices. Our experiments on GQA dataset show that GraphVQA outperforms the state-of-the-art accuracy by a large margin (88.43{\%} vs. 94.78{\%})."
}