{"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/cosmo-contextualized-scene-modeling-with","title":"COSMO: Contextualized Scene Modeling with Boltzmann Machines","arxiv_id":"1807.00511","date":"2018-07-02","proceeding":null,"authors":["Ilker Bozcan","Sinan Kalkan"],"abstract":"Scene modeling is very crucial for robots that need to perceive, reason about\nand manipulate the objects in their environments. In this paper, we adapt and\nextend Boltzmann Machines (BMs) for contextualized scene modeling. Although\nthere are many models on the subject, ours is the first to bring together\nobjects, relations, and affordances in a highly-capable generative model. For\nthis end, we introduce a hybrid version of BMs where relations and affordances\nare introduced with shared, tri-way connections into the model. Moreover, we\ncontribute a dataset for relation estimation and modeling studies. We evaluate\nour method in comparison with several baselines on object estimation,\nout-of-context object detection, relation estimation, and affordance estimation\ntasks. Moreover, to illustrate the generative capability of the model, we show\nseveral example scenes that the model is able to generate.","url_abs":"http://arxiv.org/abs/1807.00511v2","url_pdf":"http://arxiv.org/pdf/1807.00511v2.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":"cosmo-contextualized-scene-modeling-with","repo_url":"https://github.com/bozcani/COSMO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}