{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/detecting-visual-relationships-with-deep","title":"Detecting Visual Relationships with Deep Relational Networks","arxiv_id":"1704.03114","date":"2017-04-11","proceeding":"CVPR 2017 7","authors":["Bo Dai","Yuqi Zhang","Dahua Lin"],"abstract":"Relationships among objects play a crucial role in image understanding.\nDespite the great success of deep learning techniques in recognizing individual\nobjects, reasoning about the relationships among objects remains a challenging\ntask. Previous methods often treat this as a classification problem,\nconsidering each type of relationship (e.g. \"ride\") or each distinct visual\nphrase (e.g. \"person-ride-horse\") as a category. Such approaches are faced with\nsignificant difficulties caused by the high diversity of visual appearance for\neach kind of relationships or the large number of distinct visual phrases. We\npropose an integrated framework to tackle this problem. At the heart of this\nframework is the Deep Relational Network, a novel formulation designed\nspecifically for exploiting the statistical dependencies between objects and\ntheir relationships. On two large datasets, the proposed method achieves\nsubstantial improvement over state-of-the-art.","url_abs":"http://arxiv.org/abs/1704.03114v2","url_pdf":"http://arxiv.org/pdf/1704.03114v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"detecting-visual-relationships-with-deep","repo_url":"https://github.com/doubledaibo/drnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-relationship-detection-on-vrd-phrase","task":"Visual Relationship Detection","dataset":"VRD Phrase Detection","model":"Dai et. al [[Dai, Zhang, and Lin2017]]","rank_in_archive_order":3,"of":7,"metrics":{"R@100":"23.45","R@50":"19.93"},"uses_additional_data":false},{"leaderboard":"/sota/visual-relationship-detection-on-vrd","task":"Visual Relationship Detection","dataset":"VRD Predicate Detection","model":"Dai et. al [[Dai, Zhang, and Lin2017]]","rank_in_archive_order":4,"of":7,"metrics":{"R@100":"81.90","R@50":"80.78"},"uses_additional_data":false},{"leaderboard":"/sota/visual-relationship-detection-on-vrd-1","task":"Visual Relationship Detection","dataset":"VRD Relationship Detection","model":"Dai et. al [[Dai, Zhang, and Lin2017]]","rank_in_archive_order":4,"of":8,"metrics":{"R@100":"20.88","R@50":"17.73"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.03114","atlas_url":"https://app.syntology.ai/?focus=1704.03114","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}