{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:55:32Z","timestamp":1782312932759,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176124"],"award-info":[{"award-number":["62176124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612262","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5725-5733","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Scene Graph Masked Variational Autoencoders for 3D Scene Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1364-6305","authenticated-orcid":false,"given":"Rui","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0851-6805","authenticated-orcid":false,"given":"Le","family":"Hui","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6099-1673","authenticated-orcid":false,"given":"Yuehui","family":"Han","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0968-8556","authenticated-orcid":false,"given":"Jianjun","family":"Qian","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6978-8834","authenticated-orcid":false,"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Sit: Self-supervised vision transformer. arXiv preprint arXiv:2104.03602","author":"Atito Sara","year":"2021","unstructured":"Sara Atito, Muhammad Awais, and Josef Kittler. 2021. Sit: Self-supervised vision transformer. arXiv preprint arXiv:2104.03602 (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1217"},{"key":"e_1_3_2_1_3_1","volume-title":"SceneSeer: 3D scene design with natural language. arXiv preprint arXiv:1703.00050","author":"Chang Angel X","year":"2017","unstructured":"Angel X Chang, Mihail Eric, Manolis Savva, and Christopher D Manning. 2017. SceneSeer: 3D scene design with natural language. arXiv preprint arXiv:1703.00050 (2017)."},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on machine learning. 1691--1703","author":"Chen Mark","year":"2020","unstructured":"Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative pretraining from pixels. In International conference on machine learning. 1691--1703."},{"key":"e_1_3_2_1_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740","author":"El-Nouby Alaaeldin","year":"2021","unstructured":"Alaaeldin El-Nouby, Gautier Izacard, Hugo Touvron, Ivan Laptev, Herv\u00e9 Jegou, and Edouard Grave. 2021. Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Migs: Meta image generation from scene graphs. arXiv preprint arXiv:2110.11918","author":"Farshad Azade","year":"2021","unstructured":"Azade Farshad, Sabrina Musatian, Helisa Dhamo, and Nassir Navab. 2021. Migs: Meta image generation from scene graphs. arXiv preprint arXiv:2110.11918 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00030"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01480"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_13"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1103-5"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Grains: Generative recursive autoencoders for indoor scenes","volume":"38","author":"Li Manyi","year":"2019","unstructured":"Manyi Li, Akshay Gadi 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, Vol. 38, 2 (2019), 1--16.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_2_1_18_1","volume-title":"Pastegan: A semi-parametric method to generate image from scene graph. Advances in neural information processing systems","author":"Li Yikang","year":"2019","unstructured":"Yikang Li, Tao Ma, Yeqi Bai, Nan Duan, Sining Wei, and Xiaogang Wang. 2019a. Pastegan: A semi-parametric method to generate image from scene graph. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00381"},{"key":"e_1_3_2_1_20_1","volume-title":"Attribute-guided image generation from layout. arXiv preprint arXiv:2008.11932","author":"Ma Ke","year":"2020","unstructured":"Ke Ma, Bo Zhao, and Leonid Sigal. 2020. Attribute-guided image generation from layout. arXiv preprint arXiv:2008.11932 (2020)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275035"},{"key":"e_1_3_2_1_22_1","volume-title":"Interactive image generation using scene graphs. arXiv preprint arXiv:1905.03743","author":"Mittal Gaurav","year":"2019","unstructured":"Gaurav Mittal, Shubham Agrawal, Anuva Agarwal, Sushant Mehta, and Tanya Marwah. 2019. Interactive image generation using scene graphs. arXiv preprint arXiv:1905.03743 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636318"},{"key":"e_1_3_2_1_27_1","volume-title":"Transformer-based image generation from scene graphs. arXiv preprint arXiv:2303.04634","author":"Sortino Renato","year":"2023","unstructured":"Renato Sortino, Simone Palazzo, and Concetto Spampinato. 2023. Transformer-based image generation from scene graphs. arXiv preprint arXiv:2303.04634 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16368"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475545"},{"key":"e_1_3_2_1_30_1","volume-title":"Using scene graph context to improve image generation. arXiv preprint arXiv:1901.03762","author":"Tripathi Subarna","year":"2019","unstructured":"Subarna Tripathi, Anahita Bhiwandiwalla, Alexei Bastidas, and Hanlin Tang. 2019. Using scene graph context to improve image generation. arXiv preprint arXiv:1901.03762 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00039"},{"key":"e_1_3_2_1_32_1","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent Pascal","year":"2010","unstructured":"Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol, and L\u00e9on Bottou. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research, Vol. 11, 12 (2010).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"e_1_3_2_1_34_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 X Chang, and Daniel Ritchie. 2019. Planit: Planning and instantiating indoor scenes with relation graph and spatial prior networks. ACM Transactions on Graphics, Vol. 38, 4 (2019), 1--15.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201362"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413722"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01492"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00878"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612262","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:03:40Z","timestamp":1755821020000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":39,"alternative-id":["10.1145\/3581783.3612262","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612262","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}