{"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/pixels-to-graphs-by-associative-embedding","title":"Pixels to Graphs by Associative Embedding","arxiv_id":"1706.07365","date":"2017-06-22","proceeding":"NeurIPS 2017 12","authors":["Alejandro Newell","Jia Deng"],"abstract":"Graphs are a useful abstraction of image content. Not only can graphs\nrepresent details about individual objects in a scene but they can capture the\ninteractions between pairs of objects. We present a method for training a\nconvolutional neural network such that it takes in an input image and produces\na full graph definition. This is done end-to-end in a single stage with the use\nof associative embeddings. The network learns to simultaneously identify all of\nthe elements that make up a graph and piece them together. We benchmark on the\nVisual Genome dataset, and demonstrate state-of-the-art performance on the\nchallenging task of scene graph generation.","url_abs":"http://arxiv.org/abs/1706.07365v2","url_pdf":"http://arxiv.org/pdf/1706.07365v2.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":"pixels-to-graphs-by-associative-embedding","repo_url":"https://github.com/umich-vl/px2graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pixels-to-graphs-by-associative-embedding","repo_url":"https://github.com/nexusapoorvacus/DeepVariationStructuredRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pixels-to-graphs-by-associative-embedding","repo_url":"https://github.com/roytseng-tw/px2graph_lab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"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":{"atlas_url":"https://app.syntology.ai/?focus=1706.07365","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}