{"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/vqa-visual-question-answering","title":"VQA: Visual Question Answering","arxiv_id":"1505.00468","date":"2015-05-03","proceeding":"ICCV 2015 12","authors":["Aishwarya Agrawal","Jiasen Lu","Stanislaw Antol","Margaret Mitchell","C. Lawrence Zitnick","Dhruv Batra","Devi Parikh"],"abstract":"We propose the task of free-form and open-ended Visual Question Answering\n(VQA). Given an image and a natural language question about the image, the task\nis to provide an accurate natural language answer. Mirroring real-world\nscenarios, such as helping the visually impaired, both the questions and\nanswers are open-ended. Visual questions selectively target different areas of\nan image, including background details and underlying context. As a result, a\nsystem that succeeds at VQA typically needs a more detailed understanding of\nthe image and complex reasoning than a system producing generic image captions.\nMoreover, VQA is amenable to automatic evaluation, since many open-ended\nanswers contain only a few words or a closed set of answers that can be\nprovided in a multiple-choice format. We provide a dataset containing ~0.25M\nimages, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the\ninformation it provides. Numerous baselines and methods for VQA are provided\nand compared with human performance. Our VQA demo is available on CloudCV\n(http://cloudcv.org/vqa).","url_abs":"http://arxiv.org/abs/1505.00468v7","url_pdf":"http://arxiv.org/pdf/1505.00468v7.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":"vqa-visual-question-answering","repo_url":"https://github.com/SDaydreamer/VisualQA_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/SatyamGaba/visual_question_answering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/SatyamGaba/vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/Shivanshu-Gupta/Visual-Question-Answering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/Shivmohith/Visual-Assistance-for-the-Blind","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/SuchismitaSahu1993/VQA-System","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/abhijit-buet/VizWiz-Visua-Question-Answering-2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/abhijit-buet/VizWiz-Visual-Question-Answering-2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/abhshkdz/neural-vqa-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/chirag26495/DAN_VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/luomancs/alternative_answer_set","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/mishajw/vocab_pie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/mkhalil1998/EC601_Group_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/moh833/VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/mokhalid-dev/Attention-based-VQA-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/ntusteeian/VQA_CNN-LSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/ramprs/grad-cam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/ruxuan666/VQA_program","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/tbmoon/basic_vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/vipulgupta1011/swapmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"vqa-visual-question-answering","repo_url":"https://github.com/yanxinyan1/yxy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"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":[{"slug":"visual-question-answering","name":"Visual Question Answering","full_name":"VQA"}],"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":"Dualnet ensemble","rank_in_archive_order":2,"of":4,"metrics":{"Percentage correct":"71.18"},"uses_additional_data":false},{"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":"LSTM + global features","rank_in_archive_order":3,"of":4,"metrics":{"Percentage correct":"69.21"},"uses_additional_data":false},{"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":"LSTM blind","rank_in_archive_order":4,"of":4,"metrics":{"Percentage correct":"61.41"},"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":"Dualnet ensemble","rank_in_archive_order":2,"of":4,"metrics":{"Percentage correct":"69.73"},"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":"LSTM + global features","rank_in_archive_order":3,"of":4,"metrics":{"Percentage correct":"65.02"},"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":"LSTM blind","rank_in_archive_order":4,"of":4,"metrics":{"Percentage correct":"57.19"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual-1","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 multiple choice","model":"LSTM Q+I","rank_in_archive_order":9,"of":10,"metrics":{"Percentage correct":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual-4","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 open ended","model":"LSTM Q+I","rank_in_archive_order":12,"of":14,"metrics":{"Percentage correct":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 2.0 open ended","model":"HDU-USYD-UNCC","rank_in_archive_order":1,"of":4,"metrics":{"Percentage correct":"68.16"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 2.0 open ended","model":"DLAIT","rank_in_archive_order":2,"of":4,"metrics":{"Percentage correct":"68.07"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.00468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.00468"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abhijit-buet/VizWiz-Visual-Question-Answering-2021","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chirag26495/DAN_VQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ramprs/grad-cam","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mokhalid-dev/Attention-based-VQA-model","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mkhalil1998/EC601_Group_Project","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vipulgupta1011/swapmix","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yanxinyan1/yxy","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/moh833/VQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SatyamGaba/vqa","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SatyamGaba/visual_question_answering","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tbmoon/basic_vqa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SuchismitaSahu1993/VQA-System","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Shivanshu-Gupta/Visual-Question-Answering","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ntusteeian/VQA_CNN-LSTM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abhijit-buet/VizWiz-Visua-Question-Answering-2021","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luomancs/alternative_answer_set","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mishajw/vocab_pie","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ruxuan666/VQA_program","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SDaydreamer/VisualQA_Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Shivmohith/Visual-Assistance-for-the-Blind","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abhshkdz/neural-vqa-attention","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_honours":2,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"repositories":4}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"d12f1716d21540a8","entry":"create_submission","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d12f1716d21540a8"}},{"code_sha256_prefix":"a4063279bd752ead","entry":"evaluate_acc","repo":"luomancs/alternative_answer_set","repo_kind":"listed","path":"evaluation/evaluation.py","file_url":"https://github.com/luomancs/alternative_answer_set/blob/HEAD/evaluation/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4063279bd752ead"}},{"code_sha256_prefix":"8d3dccfefd226953","entry":"evaluate_metrix1","repo":"luomancs/alternative_answer_set","repo_kind":"listed","path":"evaluation/evaluation.py","file_url":"https://github.com/luomancs/alternative_answer_set/blob/HEAD/evaluation/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d3dccfefd226953"}},{"code_sha256_prefix":"0cf6e2086607dd93","entry":"extract_answers","repo":"chirag26495/DAN_VQA","repo_kind":"listed","path":"utils/build_vqa_inputs.py","file_url":"https://github.com/chirag26495/DAN_VQA/blob/HEAD/utils/build_vqa_inputs.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0cf6e2086607dd93"}},{"code_sha256_prefix":"6d3a7a351f38eccd","entry":"predict_answers","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6d3a7a351f38eccd"}},{"code_sha256_prefix":"f3406c3db2da10b5","entry":"preprocess","repo":"moh833/VQA","repo_kind":"listed","path":"Evaluation/evaluate_VQA_1.py","file_url":"https://github.com/moh833/VQA/blob/HEAD/Evaluation/evaluate_VQA_1.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f3406c3db2da10b5"}},{"code_sha256_prefix":"5c4bf041a6c83301","entry":"vqa_processing","repo":"tbmoon/basic_vqa","repo_kind":"listed","path":"utils/build_vqa_inputs.py","file_url":"https://github.com/tbmoon/basic_vqa/blob/HEAD/utils/build_vqa_inputs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c4bf041a6c83301"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}