{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T14:09:59Z","timestamp":1782828599320,"version":"3.54.5"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang Province Program","award":["2024C03263"],"award-info":[{"award-number":["2024C03263"]}]},{"name":"Zhejiang Province Program","award":["2022C01222"],"award-info":[{"award-number":["2022C01222"]}]},{"name":"Zhejiang Province Program","award":["2023C03199"],"award-info":[{"award-number":["2023C03199"]}]},{"name":"Zhejiang Province Program","award":["2023C03201"],"award-info":[{"award-number":["2023C03201"]}]},{"name":"Zhejiang Province Program","award":["LZ25F020006"],"award-info":[{"award-number":["LZ25F020006"]}]},{"name":"National Program of China","award":["62172365"],"award-info":[{"award-number":["62172365"]}]},{"name":"National Program of China","award":["19ZDA197"],"award-info":[{"award-number":["19ZDA197"]}]},{"name":"Macau Project: Key Technology Research and Display System Development for New Personalized Controllable Dressing Dynamic Display, Ningbo Science and Technology Plan Project","award":["2025Z052"],"award-info":[{"award-number":["2025Z052"]}]},{"name":"Macau Project: Key Technology Research and Display System Development for New Personalized Controllable Dressing Dynamic Display, Ningbo Science and Technology Plan Project","award":["2025Z062"],"award-info":[{"award-number":["2025Z062"]}]},{"name":"Macau Project: Key Technology Research and Display System Development for New Personalized Controllable Dressing Dynamic Display, Ningbo Science and Technology Plan Project","award":["2022Z167"],"award-info":[{"award-number":["2022Z167"]}]},{"name":"Macau Project: Key Technology Research and Display System Development for New Personalized Controllable Dressing Dynamic Display, Ningbo Science and Technology Plan Project","award":["2023Z137"],"award-info":[{"award-number":["2023Z137"]}]},{"name":"Macau Project: Key Technology Research and Display System Development for New Personalized Controllable Dressing Dynamic Display, Ningbo Science and Technology Plan Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcsvt.2025.3637822","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:59:56Z","timestamp":1764269996000},"page":"5274-5287","source":"Crossref","is-referenced-by-count":1,"title":["IP-Controller: Decomposition and Optimization of Cross-Attention Maps for Accurate Subject-Driven Text-to-Image Diffusion Generation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2902-8086","authenticated-orcid":false,"given":"Junsheng","family":"Luan","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2938-527X","authenticated-orcid":false,"given":"Guangyuan","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8966-1328","authenticated-orcid":false,"given":"Zhanjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4791-454X","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7994-6725","authenticated-orcid":false,"given":"Wei","family":"Xing","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, 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"},{"issue":"47","key":"ref4","first-page":"2249","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00246"},{"key":"ref6","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01767"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3409184"},{"key":"ref9","first-page":"13781","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Meng"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00979"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01764"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref13","article-title":"What the DAAM: Interpreting stable diffusion using cross attention","author":"Tang","year":"2022","journal-title":"arXiv:2210.04885"},{"key":"ref14","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530747"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01429-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3347971"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3351601"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3294261"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref24","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref25","first-page":"1069","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Gal"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3369757"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01461"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00816"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00771"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"ref35","first-page":"14369","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hertz"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00685"},{"key":"ref38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref39","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref40","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref41","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00559"},{"key":"ref44","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref45","first-page":"1","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho"},{"key":"ref46","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref47","article-title":"HunyuanCustom: A multimodal-driven architecture for customized video generation","author":"Hu","year":"2025","journal-title":"arXiv:2505.04512"},{"key":"ref48","article-title":"VACE: All-in-one video creation and editing","author":"Jiang","year":"2025","journal-title":"arXiv:2503.07598"},{"key":"ref49","article-title":"Phantom: Subject-consistent video generation via cross-modal alignment","author":"Liu","year":"2025","journal-title":"arXiv:2502.11079"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11475579\/11270863.pdf?arnumber=11270863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:04:05Z","timestamp":1775592245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":49,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3637822","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}