{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:34:19Z","timestamp":1771634059608,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":21,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613432","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"9336-9339","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Text-to-Metaverse: Towards a Digital Twin-Enabled Multimodal Conditional Generative Metaverse"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8904-8240","authenticated-orcid":false,"given":"Ahmed","family":"Elhagry","sequence":"first","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, UAE"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Praveen Kumar Reddy Maddikunta, and Thippa Reddy Gadekallu","author":"Chengoden Rajeswari","year":"2023","unstructured":"Rajeswari Chengoden, Nancy Victor, Thien Huynh-The, Gokul Yenduri, Rutvij H Jhaveri, Mamoun Alazab, Sweta Bhattacharya, Pawan Hegde, Praveen Kumar Reddy Maddikunta, and Thippa Reddy Gadekallu. 2023. Metaverse for Healthcare: A Survey on Potential Applications, Challenges and Future Directions. IEEE Access (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/pr10040744"},{"key":"e_1_3_2_1_3_1","volume-title":"Digital twins: The convergence of multimedia technologies","author":"Saddik Abdulmotaleb El","year":"2018","unstructured":"Abdulmotaleb El Saddik. 2018. Digital twins: The convergence of multimedia technologies. IEEE multimedia 25, 2 (2018), 87--92."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Stefan Mihai Mahnoor Yaqoob Dang V Hung William Davis Praveer Towakel Mohsin Raza Mehmet Karamanoglu Balbir Barn Dattaprasad Shetve Raja V Prasad et al. 2022. Digital twins: a survey on enabling technologies challenges trends and future prospects. IEEE Communications Surveys & Tutorials (2022).","DOI":"10.1109\/COMST.2022.3208773"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_8_1","volume-title":"Technologies, Applications, and Challenges. arXiv preprint arXiv:2111.09673","author":"Ning Huansheng","year":"2021","unstructured":"Huansheng Ning, Hang Wang, Yujia Lin, Wenxi Wang, Sahraoui Dhelim, Fadi Farha, Jianguo Ding, and Mahmoud Daneshmand. 2021. A Survey on Metaverse: the State-of-the-art, Technologies, Applications, and Challenges. arXiv preprint arXiv:2111.09673 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"A metaverse: taxonomy, components, applications, and open challenges","author":"Park Sang-Min","year":"2022","unstructured":"Sang-Min Park and Young-Gab Kim. 2022. A metaverse: taxonomy, components, applications, and open challenges. IEEE access 10 (2022), 4209--4251."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1060--1069","author":"Reed Scott","year":"2016","unstructured":"Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. In International conference on machine learning. PMLR, 1060--1069."},{"key":"e_1_3_2_1_12_1","volume-title":"Virtual reality, augmented reality, and mixed reality in education: A brief overview. Current and prospective applications of virtual reality in higher education","author":"Sala Nicoletta","year":"2021","unstructured":"Nicoletta Sala. 2021. Virtual reality, augmented reality, and mixed reality in education: A brief overview. Current and prospective applications of virtual reality in higher education (2021), 48--73."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00687"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-017-0233-1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101308"},{"key":"e_1_3_2_1_16_1","volume-title":"Learning a probabilistic latent space of object shapes via 3d generative adversarial modeling. Advances in neural information processing systems 29","author":"Wu Jiajun","year":"2016","unstructured":"Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. 2016. Learning a probabilistic latent space of object shapes via 3d generative adversarial modeling. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2807588"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_20_1","volume-title":"Stackgan: Realistic image synthesis with stacked generative adversarial networks","author":"Zhang Han","year":"2018","unstructured":"Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris N Metaxas. 2018. Stackgan: Realistic image synthesis with stacked generative adversarial networks. IEEE transactions on pattern analysis and machine intelligence 41, 8 (2018), 1947--1962."},{"key":"e_1_3_2_1_21_1","volume-title":"Toward multimodal image-to-image translation. Advances in neural information processing systems 30","author":"Zhu Jun-Yan","year":"2017","unstructured":"Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A Efros, Oliver Wang, and Eli Shechtman. 2017. Toward multimodal image-to-image translation. Advances in neural information processing systems 30 (2017)."}],"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\/3581783.3613432","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:49Z","timestamp":1755820849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":21,"alternative-id":["10.1145\/3581783.3613432","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613432","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"}}]}}