{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/graph-structured-representations-for-visual","title":"Graph-Structured Representations for Visual Question Answering","arxiv_id":"1609.05600","date":"2016-09-19","proceeding":"CVPR 2017 7","authors":["Damien Teney","Lingqiao Liu","Anton Van Den Hengel"],"abstract":"This paper proposes to improve visual question answering (VQA) with\nstructured representations of both scene contents and questions. A key\nchallenge in VQA is to require joint reasoning over the visual and text\ndomains. The predominant CNN/LSTM-based approach to VQA is limited by\nmonolithic vector representations that largely ignore structure in the scene\nand in the form of the question. CNN feature vectors cannot effectively capture\nsituations as simple as multiple object instances, and LSTMs process questions\nas series of words, which does not reflect the true complexity of language\nstructure. We instead propose to build graphs over the scene objects and over\nthe question words, and we describe a deep neural network that exploits the\nstructure in these representations. This shows significant benefit over the\nsequential processing of LSTMs. The overall efficacy of our approach is\ndemonstrated by significant improvements over the state-of-the-art, from 71.2%\nto 74.4% in accuracy on the \"abstract scenes\" multiple-choice benchmark, and\nfrom 34.7% to 39.1% in accuracy over pairs of \"balanced\" scenes, i.e. images\nwith fine-grained differences and opposite yes/no answers to a same question.","url_abs":"http://arxiv.org/abs/1609.05600v2","url_pdf":"http://arxiv.org/pdf/1609.05600v2.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":[],"tasks":[{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-coco-visual-3","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) abstract 1.0 multiple choice","model":"Graph VQA","rank_in_archive_order":1,"of":4,"metrics":{"Percentage correct":"74.37"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual-2","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) abstract images 1.0 open ended","model":"Graph VQA","rank_in_archive_order":1,"of":4,"metrics":{"Percentage correct":"70.42"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.05600","atlas_url":"https://app.syntology.ai/?focus=1609.05600","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1609.05600"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1609.05600\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1609.05600"},"call":"get_concepts_for_paper(arxiv_id=\"1609.05600\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"820c92b05a0668602a898aff0b30de0f59a8f033eaa65e4b48e78ee93e7b34db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}