{"url":"/sota/visual-question-answering-on-coco-visual","task":{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","note":null},"dataset":{"name":"COCO Visual Question Answering (VQA) real images 2.0 open ended","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"**Visual Question Answering (VQA)** is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.\r\n\r\nImage Source: [visualqa.org](https://visualqa.org/)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Percentage correct"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Percentage correct":null}},"counts":{"rows":4,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"HDU-USYD-UNCC","metrics":{"Percentage correct":"68.16"},"uses_additional_data":false,"paper_date":"2015-05-03","paper":"/paper/vqa-visual-question-answering","paper_url":"http://arxiv.org/abs/1505.00468v7","paper_title":"VQA: Visual Question Answering","code":"https://github.com/ramprs/grad-cam","n_code_links":21,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":6}},{"rank_in_archive_order":2,"model":"DLAIT","metrics":{"Percentage correct":"68.07"},"uses_additional_data":false,"paper_date":"2015-05-03","paper":"/paper/vqa-visual-question-answering","paper_url":"http://arxiv.org/abs/1505.00468v7","paper_title":"VQA: Visual Question Answering","code":"https://github.com/ramprs/grad-cam","n_code_links":21,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":6}},{"rank_in_archive_order":3,"model":"MCB","metrics":{"Percentage correct":"62.27"},"uses_additional_data":false,"paper_date":"2016-12-02","paper":"/paper/making-the-v-in-vqa-matter-elevating-the-role","paper_url":"http://arxiv.org/abs/1612.00837v3","paper_title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","code":"https://github.com/necla-ml/SNLI-VE","n_code_links":7,"syntology":null},{"rank_in_archive_order":4,"model":"d-LSTM+nI","metrics":{"Percentage correct":"54.22"},"uses_additional_data":false,"paper_date":"2016-12-02","paper":"/paper/making-the-v-in-vqa-matter-elevating-the-role","paper_url":"http://arxiv.org/abs/1612.00837v3","paper_title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","code":"https://github.com/necla-ml/SNLI-VE","n_code_links":7,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":12,"n_unverified":2,"n_samples":14,"n_pointer_only_licence":12,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}