{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:07:03Z","timestamp":1790273223966,"version":"4.1.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grant Council - General Research Fund Scheme","award":["17202422"],"award-info":[{"award-number":["17202422"]}]},{"name":"Theme-based Research","award":["T45-701\/22-R"],"award-info":[{"award-number":["T45-701\/22-R"]}]},{"name":"JC STEM Lab of Robotics for Soft Materials"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3692948","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:57:21Z","timestamp":1778788641000},"page":"11543-11559","source":"Crossref","is-referenced-by-count":3,"title":["S$^{2}$VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9538-5879","authenticated-orcid":false,"given":"Peng","family":"Dai","sequence":"first","affiliation":[{"name":"University of Hong Kong, Pok Fu Lam","department":["Department of Electrical and Electronic Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feitong","family":"Tan","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiangeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-8280","authenticated-orcid":false,"given":"Yihua","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Pok Fu Lam","department":["Department of Electrical and Electronic Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Futschik","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruofei","family":"Du","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Fanello","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5386-8872","authenticated-orcid":false,"given":"Yinda","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-1626","authenticated-orcid":false,"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Pok Fu Lam","department":["Department of Electrical and Electronic Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00416"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref5","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3692948"},{"key":"ref14","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2027"},{"key":"ref17","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref19","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref22","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref23","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00538"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00063"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530755"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/167"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00404"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"ref39","article-title":"Fast view synthesis of casual videos","author":"Lee","year":"2023"},{"key":"ref40","article-title":"Go-NeRF: Generating virtual objects in neural radiance fields","author":"Dai","year":"2024"},{"key":"ref41","article-title":"GaussianFlow: Splatting gaussian dynamics for 4D content creation","author":"Gao","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00636"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581312"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00737"},{"key":"ref46","article-title":"VideoMV: Consistent multi-view generation based on large video generative model","author":"Zuo","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01229"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01704"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00785"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596772"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02372"},{"key":"ref59","article-title":"MonST3R: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref64","first-page":"1","article-title":"FVD: A new metric for video generation","author":"Unterthiner"},{"key":"ref65","volume-title":"A Technique for the Measurement of Attitudes","author":"Likert","year":"1932"},{"key":"ref66","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref67","article-title":"Clip-score: CLIP score for PyTorch","author":"Zhengwentai","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11517542.pdf?arnumber=11517542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:27:52Z","timestamp":1790270872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11517542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":67,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3692948","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}