{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T20:02:09Z","timestamp":1784664129581,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62171282"],"award-info":[{"award-number":["62171282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100003399","name":"STCSM","doi-asserted-by":"crossref","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3685069","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:44:56Z","timestamp":1781293496000},"page":"7475-7490","source":"Crossref","is-referenced-by-count":0,"title":["Text-Driven Relation Manipulation of Diffusion Imagery"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7862-840X","authenticated-orcid":false,"given":"Yiming","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0674-9296","authenticated-orcid":false,"given":"Peng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Hu","sequence":"additional","affiliation":[{"name":"Ant Group","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Qin","sequence":"additional","affiliation":[{"name":"Ant Group","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1956-694X","authenticated-orcid":false,"given":"Jun","family":"Sun","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6508-4469","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref3","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00091"},{"key":"ref7","article-title":"Highly personalized text embedding for image manipulation by stable diffusion","author":"Han","year":"2023","journal-title":"arXiv:2303.08767"},{"key":"ref8","first-page":"2065","article-title":"Controllable text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref9","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref10","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv:2108.01073"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref16","article-title":"Region-aware diffusion for zero-shot text-driven image editing","author":"Huang","year":"2023","journal-title":"arXiv:2302.11797"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-03151-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref20","first-page":"9598","article-title":"Visual instruction inversion: Image editing via image prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28111"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01044"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"ref24","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref26","article-title":"Training-free layout control with cross-attention guidance","author":"Chen","year":"2023","journal-title":"arXiv:2304.03373"},{"key":"ref27","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022","journal-title":"arXiv:2212.05032"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161985"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref33","article-title":"A theoretical justification for image inpainting using denoising diffusion probabilistic models","author":"Rout","year":"2023","journal-title":"arXiv:2302.01217"},{"key":"ref34","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Bar-Tal","year":"2023"},{"key":"ref35","article-title":"Mixture of diffusers for scene composition and high resolution image generation","author":"Jim\u00e9nez","year":"2023","journal-title":"arXiv:2302.02412"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref37","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref40","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref41","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref42","article-title":"LoCo: Locally constrained training-free layout-to-image synthesis","author":"Zhao","year":"2023","journal-title":"arXiv:2311.12342"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0714"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687604"},{"key":"ref48","first-page":"31194","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Poole"},{"key":"ref49","first-page":"73232","article-title":"Collaborative score distillation for consistent visual editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00761"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3544777"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1447"},{"key":"ref55","first-page":"6437","article-title":"Countering language drift with seeded iterated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref57","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref58","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref60","article-title":"An edit friendly DDPM noise space: Inversion and manipulations","author":"Huberman-Spiegelglas","year":"2023","journal-title":"arXiv:2304.06140"},{"key":"ref61","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":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref63","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":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11561833.pdf?arnumber=11561833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T19:03:09Z","timestamp":1784660589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11561833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3685069","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}