{"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/linknet-relational-embedding-for-scene-graph","title":"LinkNet: Relational Embedding for Scene Graph","arxiv_id":"1811.06410","date":"2018-11-15","proceeding":"NeurIPS 2018 12","authors":["Sanghyun Woo","Dahun Kim","Donghyeon Cho","In So Kweon"],"abstract":"Objects and their relationships are critical contents for image\nunderstanding. A scene graph provides a structured description that captures\nthese properties of an image. However, reasoning about the relationships\nbetween objects is very challenging and only a few recent works have attempted\nto solve the problem of generating a scene graph from an image. In this paper,\nwe present a method that improves scene graph generation by explicitly modeling\ninter-dependency among the entire object instances. We design a simple and\neffective relational embedding module that enables our model to jointly\nrepresent connections among all related objects, rather than focus on an object\nin isolation. Our method significantly benefits the main part of the scene\ngraph generation task: relationship classification. Using it on top of a basic\nFaster R-CNN, our model achieves state-of-the-art results on the Visual Genome\nbenchmark. We further push the performance by introducing global context\nencoding module and geometrical layout encoding module. We validate our final\nmodel, LinkNet, through extensive ablation studies, demonstrating its efficacy\nin scene graph generation.","url_abs":"http://arxiv.org/abs/1811.06410v1","url_pdf":"http://arxiv.org/pdf/1811.06410v1.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":"linknet-relational-embedding-for-scene-graph","repo_url":"https://github.com/jiayan97/linknet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"linknet-relational-embedding-for-scene-graph","repo_url":"https://github.com/2023-MindSpore-1/ms-code-211/tree/main/dlinknet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"linknet-relational-embedding-for-scene-graph","repo_url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/dlinknet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.06410","atlas_url":"https://app.syntology.ai/?focus=1811.06410","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}