{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T05:46:48Z","timestamp":1775540808412,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2034"],"award-info":[{"award-number":["U22B2034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62421003"],"award-info":[{"award-number":["62421003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LD24F020011"],"award-info":[{"award-number":["LD24F020011"]}]},{"name":"Beijing Municipal Science and Technology","award":["Z241100001324002"],"award-info":[{"award-number":["Z241100001324002"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484681"],"award-info":[{"award-number":["20240484681"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651030","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:39:22Z","timestamp":1767638362000},"page":"2578-2592","source":"Crossref","is-referenced-by-count":0,"title":["DreamJourney: Perpetual View Generation With Video Diffusion Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4561-2469","authenticated-orcid":false,"given":"Bo","family":"Pan","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9058-5051","authenticated-orcid":false,"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"HiDream.ai, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8898","authenticated-orcid":false,"given":"Yingwei","family":"Pan","sequence":"additional","affiliation":[{"name":"HiDream.ai, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"HiDream.ai, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8365-4741","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"HiDream.ai, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01419"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00355"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref6","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref7","first-page":"1","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref8","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref10","first-page":"39897","article-title":"SceneScape: Text-driven consistent scene generation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Fridman","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2009.2031133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_10"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00468"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681634"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350937"},{"key":"ref21","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350593"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3037461"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160297"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3224327"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183402"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref28","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022"},{"key":"ref29","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301226"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3371218"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2849602"},{"key":"ref36","article-title":"Video generation models as world simulators","author":"OpenAI","year":"2024"},{"key":"ref37","article-title":"Open-Sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref38","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref39","article-title":"EasyAnimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535321"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379457"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref43","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Wei","year":"2024"},{"key":"ref44","article-title":"GPT-4 technical report","author":"Achiam","year":"2024"},{"key":"ref45","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang","year":"2025"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329179.pdf?arnumber=11329179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:50:41Z","timestamp":1775537441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651030","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}