{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:04:21Z","timestamp":1777889061544,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01527","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16451-16460","source":"Crossref","is-referenced-by-count":0,"title":["Addressing Text Embedding Leakage in Diffusion-Based Image Editing"],"prefix":"10.1109","author":[{"given":"Sunung","family":"Mun","sequence":"first","affiliation":[{"name":"Graduate School of AI, POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhwan","family":"Nam","sequence":"additional","affiliation":[{"name":"Graduate School of AI, POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunghyun","family":"Cho","sequence":"additional","affiliation":[{"name":"Graduate School of AI, POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungseul","family":"Ok","sequence":"additional","affiliation":[{"name":"Graduate School of AI, POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref6","article-title":"Direct inversion: Optimization-free text-driven real image editing with diffusion models","author":"Elarabawy","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681199"},{"key":"ref8","author":"Luo","year":"2023","journal-title":"Latent consistency models: Synthesizing highresolution images with few-step inference"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01864"},{"key":"ref10","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref13","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"137646137672","article-title":"Token merging for trainingfree semantic binding in text-to-image synthesis","volume":"37","author":"Hu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Paralleledits: Efficient multiaspect text-driven image editing with attention grouping","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Huang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref17","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450462"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref20","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0157"},{"key":"ref24","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.723"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref29","article-title":"Inversion-free image editing with natural language","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1143"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28622"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444434.pdf?arnumber=11444434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:06Z","timestamp":1777611966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01527","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}