{"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":3,"n_unverified":4,"n_pointer_only":0}}},{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":37,"tagged_in_all":82,"items":[{"url":"/paper/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":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/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":7,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/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","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","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","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":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/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","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","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","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","title":"Distance-Aware Occlusion Detection with Focused Attention","date":"2022-08-23","arxiv_id":"2208.11122","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":3}},{"url":"/paper/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":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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","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","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","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","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","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","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","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","title":"Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection","date":"2019-02-15","arxiv_id":"1902.05829","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}