{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:20Z","timestamp":1777865300000,"version":"3.51.4"},"reference-count":53,"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"}],"funder":[{"DOI":"10.13039\/501100004052","name":"King Abdullah University of Science and Technology (KAUST)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01481","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15960-15970","source":"Crossref","is-referenced-by-count":0,"title":["EditClip: Representation Learning for Image Editing"],"prefix":"10.1109","author":[{"given":"Qian","family":"Wang","sequence":"first","affiliation":[{"name":"KAUST,Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksandar","family":"Cvejic","sequence":"additional","affiliation":[{"name":"KAUST,Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelrahman","family":"Eldesokey","sequence":"additional","affiliation":[{"name":"KAUST,Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wonka","sequence":"additional","affiliation":[{"name":"KAUST,Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"ref2","article-title":"Sega: Instructing diffusion using semantic dimensions","author":"Brack","year":"2023","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00045"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_21"},{"key":"ref8","article-title":"Custom-edit: Text-guided image editing with customized diffusion models","author":"Choi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730747"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ArXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref14","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref15","volume-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing","author":"Ge","year":"2024"},{"key":"ref16","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2024","journal-title":"ICLR"},{"key":"ref17","article-title":"Motion guidance: Diffusion-based image editing with differentiable motion estimators","volume-title":"International Conference on Learning Representations","author":"Geng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00424"},{"key":"ref20","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref26","article-title":"Generating images with multimodal language models","author":"Yu Koh","year":"2023","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Flowedit: Inversion-free text-based editing using pre-trained flow models","author":"Kulikov","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","volume-title":"Labs. Flux. 1 [dev]","author":"Forest","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01710"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0421"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref34","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref38","article-title":"Reedit: Multimodal exemplar-based image editing with diffusion models","author":"Srivastava","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3592451"},{"key":"ref41","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref42","article-title":"MDP: A generalized framework for text-guided image editing by manipulating the diffusion path","author":"Wang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0374"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00678"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00903"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00903"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2115"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref53","article-title":"Instructbrush: Learning attention-based instruction optimization for image editing","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"}],"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\/11444990.pdf?arnumber=11444990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:58Z","timestamp":1777529578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01481","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}