{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:53:20Z","timestamp":1780764800846,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Young Scientists Fund of NSFC","award":["62406035"],"award-info":[{"award-number":["62406035"]}]},{"DOI":"10.13039\/501100001809","name":"Intelligent Logistics Interdisciplinary Team Project of Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","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":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3542180","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T13:36:04Z","timestamp":1739540164000},"page":"7167-7180","source":"Crossref","is-referenced-by-count":3,"title":["E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance"],"prefix":"10.1109","volume":"35","author":[{"given":"Tianrui","family":"Huang","sequence":"first","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pu","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3857-3982","authenticated-orcid":false,"given":"Lu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2834-9461","authenticated-orcid":false,"given":"Chun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7712-3322","authenticated-orcid":false,"given":"Mengjie","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-2200","authenticated-orcid":false,"given":"Qing","family":"Song","sequence":"additional","affiliation":[{"name":"School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref3","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref4","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref5","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv:2301.00704"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref7","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687813"},{"key":"ref10","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref13","first-page":"1","article-title":"Free-Bloom: Zero-shot text-to-video generator with LLM director and LDM animator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Huang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref15","article-title":"Deep learning technique for human parsing: A survey and outlook","author":"Yang","year":"2023","journal-title":"arXiv:2301.00394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09604-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217413"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382633"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441713"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3407206"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3455576"},{"key":"ref22","article-title":"Prompt-to-Prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref24","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv:2210.11427"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286841"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref33","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref34","article-title":"Cross-image attention for zero-shot appearance transfer","author":"Alaluf","year":"2023","journal-title":"arXiv:2311.03335"},{"key":"ref35","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-40442-0_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00419"},{"key":"ref38","article-title":"LSAP: Rethinking inversion fidelity, perception and editability in GAN latent space","author":"Cao","year":"2022","journal-title":"arXiv:2209.12746"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3391348"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3213662"},{"key":"ref42","first-page":"1","article-title":"Text-adaptive generative adversarial networks: Manipulating images with natural language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nam"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00790"},{"key":"ref44","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref45","first-page":"16890","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ding"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref48","article-title":"Improving tuning-free real image editing with proximal guidance","author":"Han","year":"2023","journal-title":"arXiv:2306.05414"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294261"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref57","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409184"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424572"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3359238"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3450493"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3383659"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3470888"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3314767"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452475"},{"key":"ref67","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref68","article-title":"Concept-centric personalization with large-scale diffusion priors","author":"Cao","year":"2023","journal-title":"arXiv:2312.08195"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28270"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27931"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref76","article-title":"SDXL-lightning: Progressive adversarial diffusion distillation","author":"Lin","year":"2024","journal-title":"arXiv:2402.13929"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10887316.pdf?arnumber=10887316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:57Z","timestamp":1767638457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":76,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3542180","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}