{"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":"/dataset/vizwiz","name":"VizWiz","full_name":"VizWiz-VQA","description_markdown":"The **VizWiz**-VQA dataset originates from a natural visual question answering setting where blind people each took an image and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. The proposed challenge addresses the following two tasks for this dataset: predict the answer to a visual question and (2) predict whether a visual question cannot be answered.\r\n\r\nSource: [https://vizwiz.org/tasks-and-datasets/vqa/](https://vizwiz.org/tasks-and-datasets/vqa/)\r\nImage Source: [https://vizwiz.org/tasks-and-datasets/vqa/](https://vizwiz.org/tasks-and-datasets/vqa/)","description_withheld":null,"homepage":"https://vizwiz.org/tasks-and-datasets/vqa/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/vizwiz-grand-challenge-answering-visual","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","first_author":"Danna Gurari","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[],"variants":["VizWiz Answer Differences 2019","VizWiz 2020 VQA","VizWiz 2020 test-dev","VizWiz 2020 test","VizWiz 2020 Answerability","VizWiz 2018 Answerability","VizWiz 2018","VizWiz"],"data_loaders":[],"num_papers_in_archive":260,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-captioning-on-vizwiz-2020-test-dev","task":"Image Captioning","dataset_variant":"VizWiz 2020 test-dev","rows":50,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"IBM Research AI","paper":null,"metrics":{"B1":"72.48","B2":"53.93","B3":"38.79","B4":"27.35","CIDEr":"80.67","METEOR":"22.21","ROUGE-L":"50.11","SPICE":"16.96"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020-vqa","task":"Visual Question Answering (VQA)","dataset_variant":"VizWiz 2020 VQA","rows":16,"metrics":["overall","yes/no","number","other","unanswerable"],"first_row_in_archive_order":{"model":"PaLI","paper":"/paper/pali-a-jointly-scaled-multilingual-language","metrics":{"overall":"73.3"},"code_links":[{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-vizwiz-2020-test","task":"Image Captioning","dataset_variant":"VizWiz 2020 test","rows":13,"metrics":["CIDEr","B1","B2","B3","B4","ROUGE-L","METEOR","SPICE"],"first_row_in_archive_order":{"model":"IBM Research AI","paper":null,"metrics":{"B1":"72.77","B2":"54.17","B3":"38.97","B4":"27.44","CIDEr":"81.04","METEOR":"22.25","ROUGE-L":"50.2","SPICE":"17.0"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2018-1","task":"Visual Question Answering (VQA)","dataset_variant":"VizWiz 2018","rows":10,"metrics":["overall","yes/no","number","other","unanswerable"],"first_row_in_archive_order":{"model":"LXR955, No Ensemble","paper":"/paper/lxmert-learning-cross-modality-encoder","metrics":{"number":"24.76","other":"39.0","overall":"55.4","unanswerable":"82.26","yes/no":"74.0"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"airsplay/lxmert","url":"https://github.com/airsplay/lxmert"},{"title":"zhegan27/VILLA","url":"https://github.com/zhegan27/VILLA"},{"title":"zhegan27/LXMERT-AdvTrain","url":"https://github.com/zhegan27/LXMERT-AdvTrain"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"itsShnik/adaptively-finetuning-transformers","url":"https://github.com/itsShnik/adaptively-finetuning-transformers"},{"title":"ghazaleh-mahmoodi/lxmert_compression","url":"https://github.com/ghazaleh-mahmoodi/lxmert_compression"},{"title":"chaitanyadwivedii/3D-Attention-is-All-You-Need","url":"https://github.com/chaitanyadwivedii/3D-Attention-is-All-You-Need"},{"title":"Mind23-2/MindCode-156","url":"https://github.com/Mind23-2/MindCode-156"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020","task":"Visual Question Answering (VQA)","dataset_variant":"VizWiz 2020 Answerability","rows":6,"metrics":["average_precision","f1_score"],"first_row_in_archive_order":{"model":"CLIP-Ensemble","paper":"/paper/less-is-more-linear-layers-on-clip-features","metrics":{"average_precision":"84.13"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-1","task":"Visual Question Answering","dataset_variant":"VizWiz","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Emu-I *","paper":"/paper/generative-pretraining-in-multimodality","metrics":{"Accuracy":"38.1"},"code_links":[{"title":"baaivision/emu","url":"https://github.com/baaivision/emu"},{"title":"doc-doc/NExT-OE","url":"https://github.com/doc-doc/NExT-OE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2018","task":"Visual Question Answering (VQA)","dataset_variant":"VizWiz 2018 Answerability","rows":1,"metrics":["average_precision","f1_score"],"first_row_in_archive_order":{"model":"ensemble_two_best","paper":null,"metrics":{"average_precision":"82.78","f1_score":"68.72"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":5,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}}}},{"paper":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}}}},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"paper":"/paper/less-is-more-linear-layers-on-clip-features","slug":"less-is-more-linear-layers-on-clip-features","title":"Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model","date":"2022-06-10","arxiv_id":"2206.05281","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/decoupled-box-proposal-and-featurization-with","slug":"decoupled-box-proposal-and-featurization-with","title":"Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering","date":"2019-09-04","arxiv_id":"1909.02097","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":3,"official":{"repos":["airsplay/lxmert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}}}},{"paper":"/paper/towards-vqa-models-that-can-read","slug":"towards-vqa-models-that-can-read","title":"Towards VQA Models That Can Read","date":"2019-04-18","arxiv_id":"1904.08920","rows_on_this_dataset":1,"code_links":7,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}}}},{"paper":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}}}},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"paper":"/paper/less-is-more-linear-layers-on-clip-features","slug":"less-is-more-linear-layers-on-clip-features","title":"Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model","date":"2022-06-10","arxiv_id":"2206.05281","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/decoupled-box-proposal-and-featurization-with","slug":"decoupled-box-proposal-and-featurization-with","title":"Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering","date":"2019-09-04","arxiv_id":"1909.02097","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":3,"official":{"repos":["airsplay/lxmert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}}}},{"paper":"/paper/towards-vqa-models-that-can-read","slug":"towards-vqa-models-that-can-read","title":"Towards VQA Models That Can Read","date":"2019-04-18","arxiv_id":"1904.08920","rows_on_this_dataset":1,"code_links":7,"syntology":null}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/vizwiz/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/vizwiz/papers/ran/1","json":"/dataset/vizwiz/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":26,"samples_ran":9,"samples_constructed":5,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":17,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":12,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020-vqa","since_archive":"/sota/visual-question-answering-on-vizwiz-2020-vqa#since-judged","papers_judged":8,"placed":1},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-1","since_archive":"/sota/visual-question-answering-on-vizwiz-1#since-judged","papers_judged":5,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"853e0d575eb412bda792c2c8e9f4d230f855f0febecb6cb1818ae4e1e9d5c535","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}