{"url":"/sota/dense-captioning-on-visual-genome","task":{"name":"Dense Captioning","url":"/task/dense-captioning","note":null},"dataset":{"name":"Visual Genome","url":"/dataset/visual-genome"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"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":["mAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher"}},"counts":{"rows":4,"rows_with_code":3,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ControlCap","metrics":{"mAP":"18.2"},"uses_additional_data":false,"paper_date":"2024-01-31","paper":"/paper/controllable-dense-captioner-with-multimodal","paper_url":"https://arxiv.org/abs/2401.17910v3","paper_title":"ControlCap: Controllable Region-level Captioning","code":"https://github.com/callsys/controlcap","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":2,"model":"GRiT (ViT-B)","metrics":{"mAP":"15.5"},"uses_additional_data":false,"paper_date":"2022-12-01","paper":"/paper/grit-a-generative-region-to-text-transformer","paper_url":"https://arxiv.org/abs/2212.00280v1","paper_title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","code":"https://github.com/JialianW/GRiT","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":3,"model":"CAG-Net","metrics":{"mAP":"10.5"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/context-and-attribute-grounded-dense","paper_url":"http://arxiv.org/abs/1904.01410v1","paper_title":"Context and Attribute Grounded Dense Captioning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"FCLN","metrics":{"mAP":"5.4"},"uses_additional_data":false,"paper_date":"2015-11-24","paper":"/paper/densecap-fully-convolutional-localization","paper_url":"http://arxiv.org/abs/1511.07571v1","paper_title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","code":"https://github.com/jcjohnson/densecap","n_code_links":1,"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":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":4,"n_samples":12,"n_pointer_only_licence":12,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":4,"n_samples":12,"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"}}}