{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/graghvqa-language-guided-graph-neural","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","arxiv_id":"2104.10283","date":"2021-04-20","proceeding":"NAACL (maiworkshop) 2021 6","authors":["Weixin Liang","Yanhao Jiang","Zixuan Liu"],"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 for 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 model by a large margin (88.43% vs. 94.78%).","url_abs":"https://arxiv.org/abs/2104.10283v2","url_pdf":"https://arxiv.org/pdf/2104.10283v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"graghvqa-language-guided-graph-neural","repo_url":"https://github.com/codexxxl/GraphVQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"graph-question-answering","task_name":"Graph Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-question-answering-on-gqa","task":"Graph Question Answering","dataset":"GQA","model":"GraphVQA","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"96.30"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.10283","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}