{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:23:22Z","timestamp":1777656202907,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008037","name":"Meta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008037","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019827","name":"Bosch","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019827","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Stanford HAI"},{"name":"Innopeak"},{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,29]]},"DOI":"10.1145\/3550469.3555426","type":"proceedings-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T11:07:54Z","timestamp":1669806474000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Scene Synthesis from Human Motion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4176-343X","authenticated-orcid":false,"given":"Sifan","family":"Ye","sequence":"first","affiliation":[{"name":"Stanford University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixing","family":"Wang","sequence":"additional","affiliation":[{"name":"Stanford University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaman","family":"Li","sequence":"additional","affiliation":[{"name":"Stanford University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis","family":"Park","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Stanford University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_3_2_3_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"e_1_3_2_3_2_1","volume-title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions. In Conference on Computer Vision and Pattern Recognition (CVPR). 15935\u201315946","author":"Bhatnagar Bharat\u00a0Lal","year":"2022","unstructured":"Bharat\u00a0Lal Bhatnagar, Xianghui Xie, Ilya\u00a0A. Petrov, Cristian Sminchisescu, Christian Theobalt, and Gerard Pons-Moll. 2022. BEHAVE: Dataset and Method for Tracking Human Object Interactions. In Conference on Computer Vision and Pattern Recognition (CVPR). 15935\u201315946."},{"key":"e_1_3_2_3_3_1","unstructured":"Bryce Blinn Alexander Ding Daniel Ritchie R\u00a0Kenny Jones Srinath Sridhar and Manolis Savva. 2021. Learning Body-Aware 3D Shape Generative Models. arXiv preprint arXiv:2112.07022(2021)."},{"key":"e_1_3_2_3_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"e_1_3_2_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344865"},{"key":"e_1_3_2_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00874"},{"key":"e_1_3_2_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"e_1_3_2_3_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_21"},{"key":"e_1_3_2_3_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_53"},{"key":"e_1_3_2_3_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"e_1_3_2_3_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"e_1_3_2_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00509"},{"key":"e_1_3_2_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"e_1_3_2_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995448"},{"key":"e_1_3_2_3_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392480"},{"key":"e_1_3_2_3_16_1","volume-title":"Stochastic Scene-Aware Motion Prediction. In International Conference on Computer Vision (ICCV). 11354\u201311364","author":"Hassan Mohamed","year":"2021","unstructured":"Mohamed Hassan, Duygu Ceylan, Ruben Villegas, Jun Saito, Jimei Yang, Yi Zhou, and Michael Black. 2021a. Stochastic Scene-Aware Motion Prediction. In International Conference on Computer Vision (ICCV). 11354\u201311364."},{"key":"e_1_3_2_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"e_1_3_2_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"e_1_3_2_3_19_1","volume-title":"International Conference on Learning Representation (ICLR).","author":"Higgins Irina","year":"2016","unstructured":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2016. beta-vae: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representation (ICLR)."},{"key":"e_1_3_2_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"key":"e_1_3_2_3_21_1","volume-title":"Symposium on Computer Animation (SCA). 214\u2013224","author":"Kovar Lucas","year":"2003","unstructured":"Lucas Kovar and Michael Gleicher. 2003. Flexible automatic motion blending with registration curves. In Symposium on Computer Animation (SCA). 214\u2013224."},{"key":"e_1_3_2_3_22_1","first-page":"1","article-title":"Grains: Generative recursive autoencoders for indoor scenes","volume":"38","author":"Li Manyi","year":"2019","unstructured":"Manyi Li, Akshay\u00a0Gadi Patil, Kai Xu, Siddhartha Chaudhuri, Owais Khan, Ariel Shamir, Changhe Tu, Baoquan Chen, Daniel Cohen-Or, and Hao Zhang. 2019b. Grains: Generative recursive autoencoders for indoor scenes. ACM Transactions on Graphics (TOG) 38, 2 (2019), 1\u201316.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01265"},{"key":"e_1_3_2_3_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"e_1_3_2_3_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_2_3_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_25"},{"key":"e_1_3_2_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/545261.545279"},{"key":"e_1_3_2_3_28_1","volume-title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis. In Advances in Neural Information Processing Systems (NeurIPS). 12013\u201312026.","author":"Paschalidou Despoina","year":"2021","unstructured":"Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, and Sanja Fidler. 2021. ATISS: Autoregressive Transformers for Indoor Scene Synthesis. In Advances in Neural Information Processing Systems (NeurIPS). 12013\u201312026."},{"key":"e_1_3_2_3_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_2_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"e_1_3_2_3_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_10"},{"key":"e_1_3_2_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"e_1_3_2_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"e_1_3_2_3_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"e_1_3_2_3_35_1","doi-asserted-by":"crossref","unstructured":"Roberta Spallone. 2015. Digital reconstruction of demolished architectural masterpieces 3D modeling and animation: the case study of Turin Horse Racing by Mollino. Handbook of research on emerging digital tools for architectural surveying modeling and representation(2015) 476\u2013509.","DOI":"10.4018\/978-1-4666-8379-2.ch017"},{"key":"e_1_3_2_3_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NIPS). 5998\u20136008."},{"key":"e_1_3_2_3_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"e_1_3_2_3_38_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3322941","article-title":"Planit: Planning and instantiating indoor scenes with relation graph and spatial prior networks","volume":"38","author":"Wang Kai","year":"2019","unstructured":"Kai Wang, Yu-An Lin, Ben Weissmann, Manolis Savva, Angel\u00a0X Chang, and Daniel Ritchie. 2019b. Planit: Planning and instantiating indoor scenes with relation graph and spatial prior networks. ACM Transactions on Graphics (TOG) 38, 4 (2019), 1\u201315.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_3_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.359"},{"key":"e_1_3_2_3_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"e_1_3_2_3_41_1","doi-asserted-by":"crossref","unstructured":"Zhe Wang Liyan Chen Shaurya Rathore Daeyun Shin and Charless Fowlkes. 2019a. Geometric pose affordance: 3d human pose with scene constraints. arXiv preprint arXiv:1905.07718(2019).","DOI":"10.1007\/978-3-031-25075-0_1"},{"key":"e_1_3_2_3_42_1","volume-title":"Hierarchical Style-based Networks for Motion Synthesis. In European Conference on Computer Vision (ECCV). 178\u2013194","author":"Xu Jingwei","year":"2020","unstructured":"Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, and Trevor Darrell. 2020. Hierarchical Style-based Networks for Motion Synthesis. In European Conference on Computer Vision (ECCV). 178\u2013194."},{"key":"e_1_3_2_3_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00393"},{"key":"e_1_3_2_3_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01115"},{"key":"e_1_3_2_3_45_1","unstructured":"Song-Hai Zhang Shao-Kui Zhang Wei-Yu Xie Cheng-Yang Luo and Hong-Bo Fu. 2020b. Fast 3d indoor scene synthesis with discrete and exact layout pattern extraction. arXiv preprint arXiv:2002.00328(2020)."},{"key":"e_1_3_2_3_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"e_1_3_2_3_47_1","volume-title":"GIMO: Gaze-Informed Human Motion Prediction in Context. In European Conference on Computer Vision (ECCV).","author":"Zheng Yang","year":"2022","unstructured":"Yang Zheng, Yanchao Yang, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, Karen Liu, and Leonidas Guibas. 2022. GIMO: Gaze-Informed Human Motion Prediction in Context. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00748"},{"key":"e_1_3_2_3_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_27"}],"event":{"name":"SA '22: SIGGRAPH Asia 2022","location":"Daegu Republic of Korea","acronym":"SA '22","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2022 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550469.3555426","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550469.3555426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:44Z","timestamp":1750182704000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550469.3555426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":49,"alternative-id":["10.1145\/3550469.3555426","10.1145\/3550469"],"URL":"https:\/\/doi.org\/10.1145\/3550469.3555426","relation":{},"subject":[],"published":{"date-parts":[[2022,11,29]]},"assertion":[{"value":"2022-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}