{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:53:19Z","timestamp":1780764799417,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["U24A20328"],"award-info":[{"award-number":["U24A20328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376137"],"award-info":[{"award-number":["62376137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476071"],"award-info":[{"award-number":["62476071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376140"],"award-info":[{"award-number":["62376140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20315"],"award-info":[{"award-number":["U23A20315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020196","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2022YQ59"],"award-info":[{"award-number":["ZR2022YQ59"]}],"id":[{"id":"10.13039\/501100020196","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":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3616964","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T17:26:53Z","timestamp":1759512413000},"page":"3874-3884","source":"Crossref","is-referenced-by-count":3,"title":["ViMAEdit: Vision-Guided and Mask-Enhanced Adaptive Editing Algorithm for Prompt-Based Image Editing"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0595-6856","authenticated-orcid":false,"given":"Kejie","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5274-4197","authenticated-orcid":false,"given":"Xuemeng","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5764","authenticated-orcid":false,"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9600-7789","authenticated-orcid":false,"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5658-5509","authenticated-orcid":false,"given":"Weili","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3391348"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3010181"},{"key":"ref3","article-title":"Diffusion model-based image editing: A survey","author":"Huang","year":"2024","journal-title":"arXiv:2402.17525"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123314"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209996"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3436900"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3213662"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref12","first-page":"1","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286841"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530708"},{"key":"ref18","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref19","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3455576"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3531917"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref27","first-page":"1","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ju"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref29","article-title":"Investigating prompt engineering in diffusion models","author":"Witteveen","year":"2022","journal-title":"arXiv:2211.15462"},{"key":"ref30","first-page":"26291","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref32","first-page":"1","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Meng"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00903"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3542180"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref37","article-title":"PFB-diff: Progressive feature blending diffusion for text-driven image editing","author":"Huang","year":"2023","journal-title":"arXiv:2306.16894"},{"key":"ref38","first-page":"1","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Couairon"},{"key":"ref39","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref41","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"L\u00fc"},{"key":"ref42","article-title":"DPM-solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022","journal-title":"arXiv:2211.01095"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2423"},{"key":"ref44","article-title":"UniPC: A unified predictor-corrector framework for fast sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhao"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref48","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":"ref49","article-title":"How much can CLIP benefit vision-and-language tasks?","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Shen"},{"key":"ref50","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref57","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Song"},{"key":"ref58","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv:2310.04378"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11192534.pdf?arnumber=11192534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:18Z","timestamp":1773086478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11192534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":58,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3616964","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}