{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:16Z","timestamp":1781713156075,"version":"3.54.5"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406135"],"award-info":[{"award-number":["62406135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241198"],"award-info":[{"award-number":["BK20241198"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01589","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17108-17118","source":"Crossref","is-referenced-by-count":3,"title":["Star: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution"],"prefix":"10.1109","author":[{"given":"Rui","family":"Xie","sequence":"first","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Southwest University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenheng","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Tai","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Cogvideox-5b","year":"2024"},{"key":"ref2","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.304"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00616"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00882"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00402"},{"key":"ref15","article-title":"Venhancer: Generative space-time enhancement for video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2701380"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_38"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00340"},{"key":"ref20","article-title":"Scaling laws for neural language models","author":"Kaplan","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_20"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01421"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref28","first-page":"378393","article-title":"Recurrent video restoration transformer with guided deformable attention","volume":"35","author":"Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372454"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref31","article-title":"Global attention mechanism: Retain information to enhance channelspatial interactions","author":"Liu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.10308948"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"ref37","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","volume-title":"Sora","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00477"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00851"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"140","key":"ref44","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00693"},{"key":"ref47","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"36081","article-title":"Rethinking alignment in video super-resolution transformers","volume":"35","author":"Shi","year":"2022","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00207"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2096"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref56","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref61","first-page":"11241","article-title":"Animesr: Learning real-world super-resolution models for animation videos","volume":"35","author":"Wu","year":"2022","journal-title":"NeurIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00632"},{"key":"ref63","author":"Xu","year":"2024","journal-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00474"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_13"},{"key":"ref68","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00320"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01692"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00059"},{"key":"ref73","article-title":"Resshift: Efficient diffusion model for image super-resolution by residual shifting","volume":"36","author":"Yue","year":"2024","journal-title":"NeurIPS"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref77","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","volume-title":"arXiv preprint","author":"Zhang","year":"2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_24"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00791"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00245"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444815.pdf?arnumber=11444815","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:29Z","timestamp":1777531589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444815\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01589","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}