{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:39Z","timestamp":1778171079296,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62272331"],"award-info":[{"award-number":["62272331"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["SCU2023D008"],"award-info":[{"award-number":["SCU2023D008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3547337","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T13:41:48Z","timestamp":1741009308000},"page":"7471-7484","source":"Crossref","is-referenced-by-count":5,"title":["TVG: A Training-Free Transition Video Generation Method With Diffusion Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6889-1247","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"first","affiliation":[{"name":"Sobey Media Intelligence Laboratory, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaosen","family":"Chen","sequence":"additional","affiliation":[{"name":"Sobey Media Intelligence Laboratory, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5726-8256","authenticated-orcid":false,"given":"Yuegen","family":"Liu","sequence":"additional","affiliation":[{"name":"Sobey Media Intelligence Laboratory, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4718-5922","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Sobey Media Intelligence Laboratory, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3306-0498","authenticated-orcid":false,"given":"Xuming","family":"Wen","sequence":"additional","affiliation":[{"name":"Sobey Media Intelligence Laboratory, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1339-2504","authenticated-orcid":false,"given":"Hongxia","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering and the Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s003710050148"},{"key":"ref2","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv:2402.17177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00756"},{"key":"ref6","first-page":"1","article-title":"SEINE: Short-to-Long video diffusion model for generative transition and prediction","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref7","article-title":"DynamiCrafter: Animating open-domain images with video diffusion priors","author":"Xing","year":"2023","journal-title":"arXiv:2310.12190"},{"key":"ref8","article-title":"Mora: Enabling generalist video generation via a multi-agent framework","author":"Yuan","year":"2024","journal-title":"arXiv:2403.13248"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_14"},{"key":"ref10","volume-title":"Kuaishou","year":"2024"},{"key":"ref11","volume-title":"ByteDance","year":"2024"},{"key":"ref12","article-title":"TC-bench: Benchmarking temporal compositionality in text-to-video and image-to-video generation","author":"Feng","year":"2024","journal-title":"arXiv:2406.08656"},{"key":"ref13","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv:2006.11239"},{"key":"ref14","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2204.03458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3450493"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441713"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3455576"},{"key":"ref18","article-title":"MagicVideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv:2211.11018"},{"key":"ref19","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":"ref20","article-title":"FiT: Flexible vision transformer for diffusion model","author":"Lu","year":"2024","journal-title":"arXiv:2402.12376"},{"key":"ref21","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv:2401.03048"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382948"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3397927"},{"key":"ref25","article-title":"ControlVideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arXiv:2305.13077"},{"key":"ref26","article-title":"MotionClone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arXiv:2406.05338"},{"key":"ref27","article-title":"MVOC: A training-free multiple video object composition method with diffusion models","author":"Wang","year":"2024","journal-title":"arXiv:2406.15829"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424435"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447821"},{"key":"ref30","first-page":"57315","article-title":"FRAG: Frequency adapting group for diffusion video editing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_21"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"ref35","first-page":"1","article-title":"Neural discrete representation learning","volume-title":"Proc. NeurIPS","volume":"30","author":"Van Den Oord"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869695"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref38","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref40","volume-title":"Gaussian Processes for Machine Learning","volume":"2","author":"Williams","year":"2006"},{"key":"ref41","article-title":"StoryDiffusion: Consistent self-attention for long-range image and video generation","author":"Zhou","year":"2024","journal-title":"arXiv:2405.01434"},{"key":"ref42","first-page":"14541","article-title":"Fast vision transformers with HiLo attention","volume-title":"Proc. NeurIPS","volume":"35","author":"Pan"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref44","volume-title":"LUMAAI","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3687761"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref47","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref48","article-title":"Interpolating between images with diffusion models","author":"Wang","year":"2023","journal-title":"arXiv:2307.12560"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1509\/jm.13.0521"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.4324\/9781410603128-8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/00913367.2001.10673646"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3115428"},{"key":"ref53","article-title":"Identifying and solving conditional image leakage in image-to-video diffusion model","author":"Zhao","year":"2024","journal-title":"arXiv:2406.15735"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10909303.pdf?arnumber=10909303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:02:17Z","timestamp":1754503337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10909303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":53,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3547337","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}