{"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/graph-r-cnn-for-scene-graph-generation","title":"Graph R-CNN for Scene Graph Generation","arxiv_id":"1808.00191","date":"2018-08-01","proceeding":"ECCV 2018 9","authors":["Jianwei Yang","Jiasen Lu","Stefan Lee","Dhruv Batra","Devi Parikh"],"abstract":"We propose a novel scene graph generation model called Graph R-CNN, that is\nboth effective and efficient at detecting objects and their relations in\nimages. Our model contains a Relation Proposal Network (RePN) that efficiently\ndeals with the quadratic number of potential relations between objects in an\nimage. We also propose an attentional Graph Convolutional Network (aGCN) that\neffectively captures contextual information between objects and relations.\nFinally, we introduce a new evaluation metric that is more holistic and\nrealistic than existing metrics. We report state-of-the-art performance on\nscene graph generation as evaluated using both existing and our proposed\nmetrics.","url_abs":"http://arxiv.org/abs/1808.00191v1","url_pdf":"http://arxiv.org/pdf/1808.00191v1.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":"graph-r-cnn-for-scene-graph-generation","repo_url":"https://github.com/ceyzaguirre4/NSM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graph-r-cnn-for-scene-graph-generation","repo_url":"https://github.com/jwyang/graph-rcnn.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graph-r-cnn-for-scene-graph-generation","repo_url":"https://github.com/microsoft/scene_graph_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-graph-generation-on-visual-genome","task":"Scene Graph Generation","dataset":"Visual Genome","model":"Graph-RCNN","rank_in_archive_order":13,"of":19,"metrics":{"Recall@50":"11.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.00191","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}