{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:17:00Z","timestamp":1778271420601,"version":"3.51.4"},"reference-count":60,"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":[{"name":"Hong Kong Research Grants Council","award":["15203025"],"award-info":[{"award-number":["15203025"]}]},{"name":"Hong Kong Research Grants Council","award":["T32-707\/22-N"],"award-info":[{"award-number":["T32-707\/22-N"]}]},{"name":"Hong Kong Research Grants Council","award":["C7076-22GF"],"award-info":[{"award-number":["C7076-22GF"]}]},{"DOI":"10.13039\/100013101","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52305557"],"award-info":[{"award-number":["52305557"]}],"id":[{"id":"10.13039\/100013101","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011930"],"award-info":[{"award-number":["2024A1515011930"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Research Institute of Advanced Manufacturing of The Hong Kong Polytechnic University"},{"name":"Department General Research Fund","award":["P0050805"],"award-info":[{"award-number":["P0050805"]}]},{"name":"Intra-Faculty Interdisciplinary Projects","award":["P0052206"],"award-info":[{"award-number":["P0052206"]}]}],"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.2026.3650934","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:42:15Z","timestamp":1767638535000},"page":"6152-6167","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Guided Fashion Fine-Grained Attribute Editing via Semantic Segmentation and Disentangled Representation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5277-0304","authenticated-orcid":false,"given":"Kexin","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0024-8116","authenticated-orcid":false,"given":"Zhiheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, Research Institute for Advanced Manufacturing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3592-7917","authenticated-orcid":false,"given":"George Q.","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, Research Institute for Advanced Manufacturing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3224190"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318216"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613806"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3603967"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3338459"},{"key":"ref6","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref8","article-title":"User-friendly image editing with minimal text input: Leveraging captioning and injection techniques","author":"Kim","year":"2023","journal-title":"arXiv:2306.02717"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35483"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888988"},{"key":"ref12","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref14","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3601213"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref17","article-title":"OmniGen2: Exploration to advanced multimodal generation","author":"Wu","year":"2025","journal-title":"arXiv:2506.18871"},{"key":"ref18","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025","journal-title":"arXiv:2507.06261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3573401"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3460"},{"key":"ref21","article-title":"Enhancing diffusion-based image synthesis with robust classifier guidance","author":"Kawar","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32192"},{"key":"ref23","article-title":"Eliminating oversaturation and artifacts of high guidance scales in diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sadat"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00895"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref26","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref27","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref28","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref29","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"ref32","first-page":"696","article-title":"Extract free dense labels from CLIP","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref34","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional CLIP","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00495"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00398"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref41","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8555-5_13"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28456"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00378"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3361181"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01883"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01437"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00548"},{"key":"ref52","first-page":"7198","article-title":"Swapping autoencoder for deep image manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_19"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02433"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01736"},{"key":"ref59","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651287"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11329013.pdf?arnumber=11329013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:25Z","timestamp":1778269345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":60,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3650934","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}