{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T02:16:21Z","timestamp":1784254581317,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":"crossref","award":["62476133"],"award-info":[{"award-number":["62476133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62576099"],"award-info":[{"award-number":["62576099"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["11300-312200502507"],"award-info":[{"award-number":["11300-312200502507"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Start-Up Research Fund of Southeast University","doi-asserted-by":"publisher","award":["RF1028625087"],"award-info":[{"award-number":["RF1028625087"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,5]]},"DOI":"10.1109\/tcsvt.2026.3652425","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:02Z","timestamp":1768255442000},"page":"6558-6571","source":"Crossref","is-referenced-by-count":1,"title":["Training-Free Controllable Text-Guided Video Editing"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2594-2574","authenticated-orcid":false,"given":"Yuanzhi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6521-5921","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Department of Content Security, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4136-7880","authenticated-orcid":false,"given":"Xiaoya","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0543-4196","authenticated-orcid":false,"given":"Zhen","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480546"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref5","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref6","first-page":"1","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485236"},{"key":"ref11","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3532495"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3548728"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3547337"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"issue":"12","key":"ref18","first-page":"1","article-title":"Edit temporal-consistent videos with image diffusion model","volume":"20","author":"Wang","year":"2024","journal-title":"ACM Trans. Multimedia Comput., Commun., Appl."},{"key":"ref19","first-page":"1","article-title":"TokenFlow: Consistent diffusion features for consistent video editing","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Geyer"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531390"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00714"},{"key":"ref24","article-title":"Paragraph-to-image generation with information-enriched diffusion model","author":"Wu","year":"2023","journal-title":"arXiv:2311.14284"},{"key":"ref25","first-page":"1","article-title":"Generating images from captions with attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mansimov"},{"key":"ref26","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref27","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-40442-0_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref30","first-page":"10215","article-title":"Glow: Generative flow with invertible 1\u00d71 convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kingma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02013"},{"key":"ref32","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref33","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref35","first-page":"8633","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref36","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv:2211.11018"},{"key":"ref37","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv:2209.14792"},{"key":"ref38","article-title":"Hierarchical spatio-temporal decoupling for text-to-video generation","author":"Qing","year":"2023","journal-title":"arXiv:2312.04483"},{"key":"ref39","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv:2308.06571"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref41","article-title":"Text2 Video-zero: Text-to-image diffusion models are zero-shot video generators","author":"Khachatryan","year":"2023","journal-title":"arXiv:2303.13439"},{"key":"ref42","article-title":"Dual-stream diffusion net for text-to-video generation","author":"Liu","year":"2023","journal-title":"arXiv:2308.08316"},{"key":"ref43","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv:2307.04725"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref47","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arXiv:2305.13077"},{"key":"ref48","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023","journal-title":"arXiv:2305.13840"},{"key":"ref49","first-page":"450","article-title":"Video editing via factorized diffusion distillation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Singer"},{"key":"ref50","article-title":"Enhancing low-cost video editing with lightweight adaptors and temporal-aware inversion","author":"He","year":"2025","journal-title":"arXiv:2501.04606"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref52","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref53","first-page":"1","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Ravi"},{"key":"ref54","article-title":"CVPR 2023 text guided video editing competition","author":"Wu","year":"2023","journal-title":"arXiv:2310.16003"},{"key":"ref55","volume-title":"Free Stock Video Footage"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref58","article-title":"Benchmarking spatial relationships in text-to-image generation","author":"Gokhale","year":"2022","journal-title":"arXiv:2212.10015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref60","first-page":"1","article-title":"FLATTEN: Optical flow-guided attention for consistent text-to-video editing","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Cong"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11343848.pdf?arnumber=11343848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:56:08Z","timestamp":1778183768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":62,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3652425","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}