{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:17:40Z","timestamp":1775578660320,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu","doi-asserted-by":"publisher","award":["BK20240414"],"award-info":[{"award-number":["BK20240414"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Suzhou Dushu Lake Science and Education Innovation District (SEID) Science and Education Leading Talent Program","award":["KJQ2024204"],"award-info":[{"award-number":["KJQ2024204"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3548728","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T13:51:20Z","timestamp":1741269080000},"page":"8436-8451","source":"Crossref","is-referenced-by-count":2,"title":["Denoising Reuse: Exploiting Inter-Frame Motion Consistency for Efficient Video Generation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9477-6939","authenticated-orcid":false,"given":"Chenyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"given":"Shuo","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4460-7907","authenticated-orcid":false,"given":"Yixuan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"given":"Xianwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6220-029X","authenticated-orcid":false,"given":"Yujiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Oxford Suzhou Centre for Advanced Research, Suzhou, China"}]},{"given":"Mingzhi","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Bath, Bath, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9299-5951","authenticated-orcid":false,"given":"Xiaochen","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, University of Glasgow, Glasgow, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-8442","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9944-0369","authenticated-orcid":false,"given":"Rui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Bayes Business School, City, University of London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-8555","authenticated-orcid":false,"given":"David A.","family":"Clifton","sequence":"additional","affiliation":[{"name":"Oxford Suzhou Centre for Advanced Research, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5428-9530","authenticated-orcid":false,"given":"Robert P.","family":"Dick","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science College of Engineering, University of Michigan, Ann Arbor, MI, USA"}]},{"given":"Qin","family":"Lv","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Colorado at Boulder, Boulder, CO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2164-8175","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-4826","authenticated-orcid":false,"given":"Tun","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2915-974X","authenticated-orcid":false,"given":"Ning","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9216-1921","authenticated-orcid":false,"given":"Li","family":"Shang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Shanghai Key Laboratory of Data Science, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref2","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ho"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref4","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref8","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023","journal-title":"arXiv:2304.08477"},{"key":"ref9","first-page":"1","article-title":"Improved techniques for training gans","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans"},{"key":"ref10","first-page":"1","article-title":"FVD: A new metric for video generation","volume-title":"Proc. Int. Conf. Learn. Represent. Workshops","author":"Unterthiner"},{"key":"ref11","article-title":"SimDA: Simple diffusion adapter for efficient video generation","author":"Xing","year":"2023","journal-title":"arXiv:2308.09710"},{"key":"ref12","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref14","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref15","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref16","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref18","article-title":"EmerDiff: Emerging pixel-level semantic knowledge in diffusion models","author":"Namekata","year":"2024","journal-title":"arXiv:2401.11739"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382948"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409184"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3397927"},{"key":"ref24","article-title":"Make-A-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv:2209.14792"},{"key":"ref25","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref26","first-page":"1","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Villegas"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3003227"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00220"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref31","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv:2307.04725"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref33","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv:2211.13221"},{"key":"ref34","article-title":"LAVIE: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2309.15103"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref36","article-title":"VideoLCM: Video latent consistency model","author":"Wang","year":"2023","journal-title":"arXiv:2312.09109"},{"key":"ref37","article-title":"Reuse and diffuse: Iterative denoising for text-to-video generation","author":"Gu","year":"2023","journal-title":"arXiv:2309.03549"},{"issue":"3","key":"ref38","first-page":"225","article-title":"Block matching algorithms for motion estimation","volume":"8","author":"Barjatya","year":"2004","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.179"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07483-z"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00631"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref47","first-page":"1651","article-title":"Neighbourhood consensus networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rocco"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01219"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02040"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271130"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233221"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892608"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910119"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80432-9_26"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102344"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA54703.2022.10005924"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_14"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01538"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_2"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00593"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref67","first-page":"61514","article-title":"Object-centric learning for real-world videos by predicting temporal feature similarities","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zadaianchuk"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00394"},{"key":"ref69","first-page":"1229","article-title":"Leveraging early-stage robustness in diffusion models for efficient and high-quality image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref70","article-title":"Label-efficient semantic segmentation with diffusion models","author":"Baranchuk","year":"2021","journal-title":"arXiv:2112.03126"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00644"},{"key":"ref72","first-page":"1","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref78","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref80","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref81","article-title":"GODIVA: Generating open-DomaIn videos from natural descriptions","author":"Wu","year":"2021","journal-title":"arXiv:2104.14806"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10915618.pdf?arnumber=10915618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:33:49Z","timestamp":1757612029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10915618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":82,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3548728","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}