{"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":"/task/visual-relationship-detection","name":"Visual Relationship Detection","slug":"visual-relationship-detection","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":82,"papers_with_code":37,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-relationship-detection-on-vrd-1","slug":"visual-relationship-detection-on-vrd-1","dataset":"VRD Relationship Detection","dataset_url":"/dataset/vrd","rows_in_archive":8,"metrics":["R@100","R@50"],"first_row_in_archive_order":{"model":"Yu et. al [[Yu et al.2017a]]","paper_title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","paper_url":"/paper/visual-relationship-detection-with-internal","paper_date":"2017-07-28","arxiv_id":"1707.09423","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-relationship-detection-on-vrd","slug":"visual-relationship-detection-on-vrd","dataset":"VRD Predicate Detection","dataset_url":"/dataset/vrd","rows_in_archive":7,"metrics":["R@100","R@50"],"first_row_in_archive_order":{"model":"Yu et. al [[Yu et al.2017a]]","paper_title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","paper_url":"/paper/visual-relationship-detection-with-internal","paper_date":"2017-07-28","arxiv_id":"1707.09423","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-relationship-detection-on-vrd-phrase","slug":"visual-relationship-detection-on-vrd-phrase","dataset":"VRD Phrase Detection","dataset_url":"/dataset/vrd","rows_in_archive":7,"metrics":["R@100","R@50"],"first_row_in_archive_order":{"model":"Yu et. al [[Yu et al.2017a]]","paper_title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","paper_url":"/paper/visual-relationship-detection-with-internal","paper_date":"2017-07-28","arxiv_id":"1707.09423","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-relationship-detection-on-visual","slug":"visual-relationship-detection-on-visual","dataset":"Visual Genome","dataset_url":"/dataset/visual-genome","rows_in_archive":1,"metrics":["R@100","R@50","mR@100","mR@50"],"first_row_in_archive_order":{"model":"PEVL","paper_title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","paper_url":"/paper/pevl-position-enhanced-pre-training-and","paper_date":"2022-05-23","arxiv_id":"2205.11169","code_links":[{"title":"thunlp/pevl","url":"https://github.com/thunlp/pevl"}],"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-relationship-detection-on-vrd-2","slug":"visual-relationship-detection-on-vrd-2","dataset":"VRD","dataset_url":"/dataset/vrd","rows_in_archive":1,"metrics":["R@50 k=1"],"first_row_in_archive_order":{"model":"Ours - v","paper_title":"Improving Visual Relation Detection using Depth Maps","paper_url":"/paper/improving-visual-relation-detection-using","paper_date":"2019-05-02","arxiv_id":"1905.00966","code_links":[{"title":"Sina-Baharlou/Depth-VRD","url":"https://github.com/Sina-Baharlou/Depth-VRD"}],"syntology":null}}],"datasets":[{"url":"/dataset/visual-genome","name":"Visual Genome","full_name":"","num_papers_in_archive":1256},{"url":"/dataset/vrd","name":"VRD","full_name":"Visual Relationship Detection dataset","num_papers_in_archive":151},{"url":"/dataset/open-images-v7","name":"Open Images V7","full_name":"","num_papers_in_archive":6},{"url":"/dataset/visual-relationship-detection-dataset","name":"Visual Relationship Detection Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/texrel","name":"TexRel","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/human-object-relationship-detection","name":"Human-Object Relationship Detection"},{"url":"/task/video-visual-relation-detection","name":"Video Visual Relation Detection"}],"parent_tasks":[{"url":"/task/scene-understanding","name":"Scene Understanding"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":82,"of":82,"of_with_code":37,"tagged_in_all":82,"counts":{"archive_papers_tagged":82,"with_a_code_link":37,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":82,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":9,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/long-tail-visual-relationship-recognition","slug":"long-tail-visual-relationship-recognition","title":"Exploring Long Tail Visual Relationship Recognition with Large Vocabulary","date":"2020-03-25","arxiv_id":"2004.00436","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-tail-visual-relationship-recognition#ran","syntology_url":"https://syntology.ai/paper/2004.00436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00436"}},"official":{"repos":["Vision-CAIR/LTVRR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/graphical-contrastive-losses-for-scene-graph","slug":"graphical-contrastive-losses-for-scene-graph","title":"Graphical Contrastive Losses for Scene Graph Parsing","date":"2019-03-07","arxiv_id":"1903.02728","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/graphical-contrastive-losses-for-scene-graph#ran","syntology_url":"https://syntology.ai/paper/1903.02728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02728"}},"official":null}},{"url":"/paper/representing-prior-knowledge-using-randomly","slug":"representing-prior-knowledge-using-randomly","title":"Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection","date":"2021-11-20","arxiv_id":"2111.10686","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/representing-prior-knowledge-using-randomly#ran","syntology_url":"https://syntology.ai/paper/2111.10686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10686"}},"official":{"repos":["jyhong0304/visual-relationship-detection-rwfn","pavliclab/aaai2022-clear2022-visual_relationship_detection-rwfn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spatial-temporal-transformer-for-dynamic","slug":"spatial-temporal-transformer-for-dynamic","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","date":"2021-07-26","arxiv_id":"2107.12309","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":4,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spatial-temporal-transformer-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2107.12309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12309"}},"official":{"repos":["yrcong/sttran"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/one-metric-to-measure-them-all-localisation","slug":"one-metric-to-measure-them-all-localisation","title":"One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks","date":"2020-11-21","arxiv_id":"2011.10772","repositories_listed":2,"syntology":null},{"url":"/paper/compensating-supervision-incompleteness-with","slug":"compensating-supervision-incompleteness-with","title":"Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation","date":"2019-10-01","arxiv_id":"1910.00462","repositories_listed":2,"syntology":null},{"url":"/paper/metor-a-unified-framework-for-mutual","slug":"metor-a-unified-framework-for-mutual","title":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","date":"2025-05-10","arxiv_id":"2505.06663","repositories_listed":1,"syntology":null},{"url":"/paper/groupwise-query-specialization-and-quality","slug":"groupwise-query-specialization-and-quality","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","date":"2024-03-26","arxiv_id":"2403.17709","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/groupwise-query-specialization-and-quality#ran","syntology_url":"https://syntology.ai/paper/2403.17709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17709"}},"official":{"repos":["mlvlab/speaq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-relationship-detection-using-mixture-of-1","slug":"video-relationship-detection-using-mixture-of-1","title":"Video Relationship Detection Using Mixture of Experts","date":"2024-03-06","arxiv_id":"2403.03994","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-for-visual","slug":"self-supervised-learning-for-visual","title":"Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction","date":"2023-11-08","arxiv_id":"2311.04834","repositories_listed":1,"syntology":null},{"url":"/paper/stupd-a-synthetic-dataset-for-spatial-and","slug":"stupd-a-synthetic-dataset-for-spatial-and","title":"STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning","date":"2023-09-13","arxiv_id":"2309.06680","repositories_listed":1,"syntology":null},{"url":"/paper/unified-visual-relationship-detection-with","slug":"unified-visual-relationship-detection-with","title":"Unified Visual Relationship Detection with Vision and Language Models","date":"2023-03-16","arxiv_id":"2303.08998","repositories_listed":1,"syntology":null},{"url":"/paper/distance-aware-occlusion-detection-with","slug":"distance-aware-occlusion-detection-with","title":"Distance-Aware Occlusion Detection with Focused Attention","date":"2022-08-23","arxiv_id":"2208.11122","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/distance-aware-occlusion-detection-with#ran","syntology_url":"https://syntology.ai/paper/2208.11122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11122"}},"official":{"repos":["yang-li-2000/distance-aware-occlusion-detection-with-focused-attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-message-passing-for-visual","slug":"neural-message-passing-for-visual","title":"Neural Message Passing for Visual Relationship Detection","date":"2022-08-08","arxiv_id":"2208.04165","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-message-passing-for-visual#ran","syntology_url":"https://syntology.ai/paper/2208.04165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04165"}},"official":{"repos":["phyllish/nmp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/pevl-position-enhanced-pre-training-and","slug":"pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","arxiv_id":"2205.11169","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pevl-position-enhanced-pre-training-and#ran","syntology_url":"https://syntology.ai/paper/2205.11169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11169"}},"official":{"repos":["thunlp/pevl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/image-scene-graph-generation-sgg-benchmark","slug":"image-scene-graph-generation-sgg-benchmark","title":"Image Scene Graph Generation (SGG) Benchmark","date":"2021-07-27","arxiv_id":"2107.12604","repositories_listed":1,"syntology":null},{"url":"/paper/recovering-the-unbiased-scene-graphs-from-the","slug":"recovering-the-unbiased-scene-graphs-from-the","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","date":"2021-07-05","arxiv_id":"2107.02112","repositories_listed":1,"syntology":null},{"url":"/paper/2-5d-visual-relationship-detection","slug":"2-5d-visual-relationship-detection","title":"2.5D Visual Relationship Detection","date":"2021-04-26","arxiv_id":"2104.12727","repositories_listed":1,"syntology":null},{"url":"/paper/reltransformer-balancing-the-visual","slug":"reltransformer-balancing-the-visual","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","date":"2021-04-24","arxiv_id":"2104.11934","repositories_listed":1,"syntology":null},{"url":"/paper/grounding-consistency-distilling-spatial","slug":"grounding-consistency-distilling-spatial","title":"Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship Detection","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lighten-learning-interactions-with-graph-and","slug":"lighten-learning-interactions-with-graph-and","title":"LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos","date":"2020-12-17","arxiv_id":"2012.09402","repositories_listed":1,"syntology":null},{"url":"/paper/visualization-of-contributions-to-open-source","slug":"visualization-of-contributions-to-open-source","title":"Visualization of Contributions to Open-Source Projects","date":"2020-10-17","arxiv_id":"2010.08874","repositories_listed":1,"syntology":null},{"url":"/paper/rvl-bert-visual-relationship-detection-with","slug":"rvl-bert-visual-relationship-detection-with","title":"Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations","date":"2020-09-10","arxiv_id":"2009.04965","repositories_listed":1,"syntology":null},{"url":"/paper/explanation-based-weakly-supervised-learning","slug":"explanation-based-weakly-supervised-learning","title":"Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks","date":"2020-06-16","arxiv_id":"2006.09562","repositories_listed":1,"syntology":null},{"url":"/paper/avr-attention-based-salient-visual","slug":"avr-attention-based-salient-visual","title":"AVR: Attention based Salient Visual Relationship Detection","date":"2020-03-16","arxiv_id":"2003.07012","repositories_listed":1,"syntology":null},{"url":"/paper/nodis-neural-ordinary-differential-scene","slug":"nodis-neural-ordinary-differential-scene","title":"NODIS: Neural Ordinary Differential Scene Understanding","date":"2020-01-14","arxiv_id":"2001.04735","repositories_listed":1,"syntology":null},{"url":"/paper/visual-relationship-detection-with-relative","slug":"visual-relationship-detection-with-relative","title":"Visual Relationship Detection with Relative Location Mining","date":"2019-11-02","arxiv_id":"1911.00713","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-relation-detection-using","slug":"improving-visual-relation-detection-using","title":"Improving Visual Relation Detection using Depth Maps","date":"2019-05-02","arxiv_id":"1905.00966","repositories_listed":1,"syntology":null},{"url":"/paper/visual-relationship-detection-with-language-1","slug":"visual-relationship-detection-with-language-1","title":"Visual Relationship Detection with Language prior and Softmax","date":"2019-04-16","arxiv_id":"1904.07798","repositories_listed":1,"syntology":null},{"url":"/paper/deeply-supervised-multimodal-attentional","slug":"deeply-supervised-multimodal-attentional","title":"Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection","date":"2019-02-15","arxiv_id":"1902.05829","repositories_listed":1,"syntology":null},{"url":"/paper/block-bilinear-superdiagonal-fusion-for","slug":"block-bilinear-superdiagonal-fusion-for","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","date":"2019-01-31","arxiv_id":"1902.00038","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/block-bilinear-superdiagonal-fusion-for#ran","syntology_url":"https://syntology.ai/paper/1902.00038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00038"}},"official":{"repos":["Cadene/block.bootstrap.pytorch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-open-images-dataset-v4-unified-image","slug":"the-open-images-dataset-v4-unified-image","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","date":"2018-11-02","arxiv_id":"1811.00982","repositories_listed":1,"syntology":null},{"url":"/paper/factorizable-net-an-efficient-subgraph-based","slug":"factorizable-net-an-efficient-subgraph-based","title":"Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation","date":"2018-06-29","arxiv_id":"1806.11538","repositories_listed":1,"syntology":null},{"url":"/paper/visual-relationship-detection-with-deep","slug":"visual-relationship-detection-with-deep","title":"Visual relationship detection with deep structural ranking","date":"2018-04-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-context-aware-interaction-recognition-1","slug":"towards-context-aware-interaction-recognition-1","title":"Towards Context-Aware Interaction Recognition for Visual Relationship Detection","date":"2017-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-variation-structured-reinforcement","slug":"deep-variation-structured-reinforcement","title":"Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection","date":"2017-03-08","arxiv_id":"1703.03054","repositories_listed":1,"syntology":null},{"url":"/paper/phrase-localization-and-visual-relationship","slug":"phrase-localization-and-visual-relationship","title":"Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues","date":"2016-11-21","arxiv_id":"1611.06641","repositories_listed":1,"syntology":null},{"url":null,"slug":"end-to-end-open-vocabulary-video-visual","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","date":"2024-09-19","arxiv_id":"2409.12499","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-vit-end-to-end-open-vocabulary","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","date":"2024-03-21","arxiv_id":"2403.14270","repositories_listed":0,"syntology":null},{"url":null,"slug":"relvae-generative-pretraining-for-few-shot","title":"RelVAE: Generative Pretraining for few-shot Visual Relationship Detection","date":"2023-11-27","arxiv_id":"2311.16261","repositories_listed":0,"syntology":null},{"url":null,"slug":"nesy4vrd-a-multifaceted-resource-for","title":"NeSy4VRD: A Multifaceted Resource for Neurosymbolic AI Research using Knowledge Graphs in Visual Relationship Detection","date":"2023-05-22","arxiv_id":"2305.13258","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-semantic-relation-generation","title":"Image Semantic Relation Generation","date":"2022-10-19","arxiv_id":"2210.11253","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-structured-representations-of-visual","title":"Learning Structured Representations of Visual Scenes","date":"2022-07-09","arxiv_id":"2207.04200","repositories_listed":0,"syntology":null},{"url":null,"slug":"vrebert-a-simple-and-flexible-transformer-for","title":"VReBERT: A Simple and Flexible Transformer for Visual Relationship Detection","date":"2022-06-18","arxiv_id":"2206.09111","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-generation-a-comprehensive-survey","title":"Scene Graph Generation: A Comprehensive Survey","date":"2022-01-03","arxiv_id":"2201.00443","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-probabilistic-graphical-model-based-on","title":"A Probabilistic Graphical Model Based on Neural-Symbolic Reasoning for Visual Relationship Detection","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bgt-net-bidirectional-gru-transformer-network","title":"BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation","date":"2021-09-11","arxiv_id":"2109.05346","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-composite-set-detection-using-part-and","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","date":"2021-05-05","arxiv_id":"2105.02170","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graphs-a-survey-of-generations-and","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","date":"2021-03-17","arxiv_id":"2104.01111","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-overcoming-false-positives-in-visual","title":"Towards Overcoming False Positives in Visual Relationship Detection","date":"2020-12-23","arxiv_id":"2012.12510","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-a-visual-relationship","title":"Constructing a Visual Relationship Authenticity Dataset","date":"2020-10-11","arxiv_id":"2010.05185","repositories_listed":0,"syntology":null},{"url":null,"slug":"bounding-box-channels-for-visual-relationship","title":"Bounding-box Channels for Visual Relationship Detection","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-graph-attention-network-for","title":"Hierarchical Graph Attention Network for Visual Relationship Detection","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fixed-size-objects-encoding-for-visual","title":"Fixed-size Objects Encoding for Visual Relationship Detection","date":"2020-05-29","arxiv_id":"2005.14600","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-relationship-detection-using-scene","title":"Visual Relationship Detection using Scene Graphs: A Survey","date":"2020-05-16","arxiv_id":"2005.08045","repositories_listed":0,"syntology":null},{"url":null,"slug":"cparr-category-based-proposal-analysis-for","title":"CPARR: Category-based Proposal Analysis for Referring Relationships","date":"2020-04-17","arxiv_id":"2004.08028","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-adaptive-semantic-logic-dasl-compiling","title":"Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks","date":"2020-03-16","arxiv_id":"2003.07344","repositories_listed":0,"syntology":null},{"url":null,"slug":"relatext-exploiting-visual-relationships-for","title":"ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks","date":"2020-03-16","arxiv_id":"2003.06999","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-relationship-detection-with-low-rank","title":"Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition","date":"2019-11-22","arxiv_id":"1911.09895","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-auxiliary-text-for-deep-1","title":"Leveraging Auxiliary Text for Deep Recognition of Unseen Visual Relationships","date":"2019-10-27","arxiv_id":"1910.12324","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-contextual-attention-for-human-object","title":"Deep Contextual Attention for Human-Object Interaction Detection","date":"2019-10-17","arxiv_id":"1910.07721","repositories_listed":0,"syntology":null},{"url":null,"slug":"union-visual-translation-embedding-for-visual","title":"Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation","date":"2019-05-28","arxiv_id":"1905.11624","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-exploring-undetermined-relationships-for","title":"On Exploring Undetermined Relationships for Visual Relationship Detection","date":"2019-05-05","arxiv_id":"1905.01595","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-semantics-for-visual","title":"Target-Tailored Source-Transformation for Scene Graph Generation","date":"2019-04-03","arxiv_id":"1904.02104","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-graph-generation-with-external","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","date":"2019-04-01","arxiv_id":"1904.00560","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimising-the-input-image-to-improve-visual","title":"Optimising the Input Image to Improve Visual Relationship Detection","date":"2019-03-26","arxiv_id":"1903.11029","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-class-imbalance-and-background-filtering","title":"On Class Imbalance and Background Filtering in Visual Relationship Detection","date":"2019-03-20","arxiv_id":"1903.08456","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-semantic-information-pursuit-a-survey","title":"Visual Semantic Information Pursuit: A Survey","date":"2019-03-13","arxiv_id":"1903.05434","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-interpretable-model-for-scene-graph","title":"An Interpretable Model for Scene Graph Generation","date":"2018-11-21","arxiv_id":"1811.09543","repositories_listed":0,"syntology":null},{"url":null,"slug":"introduction-to-the-1st-place-winning-model","title":"Introduction to the 1st Place Winning Model of OpenImages Relationship Detection Challenge","date":"2018-11-01","arxiv_id":"1811.00662","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-problem-reduction-approach-for-visual","title":"A Problem Reduction Approach for Visual Relationships Detection","date":"2018-09-26","arxiv_id":"1809.09828","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-dependent-diffusion-network-for","title":"Context-Dependent Diffusion Network for Visual Relationship Detection","date":"2018-09-11","arxiv_id":"1809.06213","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-visual-relationship-detection-using","title":"Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions","date":"2018-09-01","arxiv_id":"1809.00204","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-information-extraction-from-images","title":"Improving Information Extraction from Images with Learned Semantic Models","date":"2018-08-27","arxiv_id":"1808.08941","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensorize-factorize-and-regularize-robust","title":"Tensorize, Factorize and Regularize: Robust Visual Relationship Learning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-relationship-detection-based-on-guided","title":"Visual Relationship Detection Based on Guided Proposals and Semantic Knowledge Distillation","date":"2018-05-28","arxiv_id":"1805.10802","repositories_listed":0,"syntology":null},{"url":null,"slug":"attend-and-interact-higher-order-object","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","date":"2017-11-16","arxiv_id":"1711.06330","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-guided-visual-relationship","title":"Natural Language Guided Visual Relationship Detection","date":"2017-11-16","arxiv_id":"1711.06032","repositories_listed":0,"syntology":null},{"url":"/paper/visual-relationship-detection-with-internal","slug":"visual-relationship-detection-with-internal","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","date":"2017-07-28","arxiv_id":"1707.09423","repositories_listed":0,"syntology":null},{"url":null,"slug":"care-about-you-towards-large-scale-human","title":"Care about you: towards large-scale human-centric visual relationship detection","date":"2017-05-28","arxiv_id":"1705.09892","repositories_listed":0,"syntology":null},{"url":null,"slug":"vip-cnn-visual-phrase-guided-convolutional","title":"ViP-CNN: Visual Phrase Guided Convolutional Neural Network","date":"2017-02-23","arxiv_id":"1702.07191","repositories_listed":0,"syntology":null},{"url":"/paper/visual-relationship-detection-with-language","slug":"visual-relationship-detection-with-language","title":"Visual Relationship Detection with Language Priors","date":"2016-07-31","arxiv_id":"1608.00187","repositories_listed":0,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/task/visual-relationship-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/visual-relationship-detection/papers/ran/1","json":"/task/visual-relationship-detection/papers/ran/1.json","rows":9}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"fd66ce4368eb146245a81884adcac2f83e455f2ef00ee6a69eff9fe6b60e877d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}