{"url":"/sota/visual-relationship-detection-on-vrd","task":{"name":"Visual Relationship Detection","url":"/task/visual-relationship-detection","note":null},"dataset":{"name":"VRD Predicate Detection","url":"/dataset/vrd"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Visual relationship detection (VRD) is one newly developed computer vision task aiming to recognize relations or interactions between objects in an image. It is a further learning task after object recognition and is essential for fully understanding images, even the visual world.","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":["R@100","R@50"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"R@100":null,"R@50":null}},"counts":{"rows":7,"rows_with_code":4,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Yu et. al [[Yu et al.2017a]]","metrics":{"R@100":"94.65","R@50":"85.64"},"uses_additional_data":false,"paper_date":"2017-07-28","paper":"/paper/visual-relationship-detection-with-internal","paper_url":"http://arxiv.org/abs/1707.09423v2","paper_title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"vrd-dsr","metrics":{"R@100":"93.18","R@50":"86.01"},"uses_additional_data":false,"paper_date":"2018-04-27","paper":"/paper/visual-relationship-detection-with-deep","paper_url":"https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Visual+relationship+detection+with+deep+structural+ranking&btnG=","paper_title":"Visual relationship detection with deep structural ranking","code":"https://github.com/GriffinLiang/vrd-dsr","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"BLOCK","metrics":{"R@100":"92.58","R@50":"86.58"},"uses_additional_data":false,"paper_date":"2019-01-31","paper":"/paper/block-bilinear-superdiagonal-fusion-for","paper_url":"http://arxiv.org/abs/1902.00038v2","paper_title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","code":"https://github.com/Cadene/block.bootstrap.pytorch","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Dai et. al [[Dai, Zhang, and Lin2017]]","metrics":{"R@100":"81.90","R@50":"80.78"},"uses_additional_data":false,"paper_date":"2017-04-11","paper":"/paper/detecting-visual-relationships-with-deep","paper_url":"http://arxiv.org/abs/1704.03114v2","paper_title":"Detecting Visual Relationships with Deep Relational Networks","code":"https://github.com/doubledaibo/drnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Peyre et. al [[Peyre et al.2017]]","metrics":{"R@100":"52.6","R@50":"52.6"},"uses_additional_data":false,"paper_date":"2017-07-29","paper":"/paper/weakly-supervised-learning-of-visual","paper_url":"http://arxiv.org/abs/1707.09472v1","paper_title":"Weakly-supervised learning of visual relations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Lu et. al [[Lu et al.2016]]","metrics":{"R@100":"47.87","R@50":"47.87"},"uses_additional_data":false,"paper_date":"2016-07-31","paper":"/paper/visual-relationship-detection-with-language","paper_url":"http://arxiv.org/abs/1608.00187v1","paper_title":"Visual Relationship Detection with Language Priors","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Zhang et. al [[Hanwang Zhang2017]]","metrics":{"R@100":"44.76","R@50":"44.76"},"uses_additional_data":false,"paper_date":"2017-02-27","paper":"/paper/visual-translation-embedding-network-for","paper_url":"http://arxiv.org/abs/1702.08319v1","paper_title":"Visual Translation Embedding Network for Visual Relation Detection","code":"https://github.com/yangxuntu/vrd","n_code_links":2,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0,"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"}}}