{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:04:40Z","timestamp":1784268280233,"version":"3.55.0"},"reference-count":57,"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\/iccv51701.2025.01487","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16026-16036","source":"Crossref","is-referenced-by-count":3,"title":["PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-Aware Mask"],"prefix":"10.1109","author":[{"given":"Jeongho","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST,Daejeon,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoiyeong","family":"Jin","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunghyun","family":"Park","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaegul","family":"Choo","sequence":"additional","affiliation":[{"name":"KAIST,Daejeon,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_24"},{"key":"ref4","article-title":"Improving image captioning descriptiveness by ranking and 11 m -based fusion","author":"Bianco","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Demystifying mmd gans","author":"Bi\u0144kowski","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","article-title":"Language models are few-shot learners","author":"Brown","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Pixart- \\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref11","article-title":"Improving diffusion models for vir-tual try-on","author":"Choi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04101"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00838"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612255"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01757"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00787"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1987.4767941"},{"key":"ref24","author":"Heusel","journal-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","volume-title":"Sdxl inpainting 0.1."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00781"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"ref30","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00576"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02522"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00664"},{"key":"ref34","article-title":"Anyfit: Controllable virtual try-on for any combination of attire across any scenario","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3796716"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612137"},{"key":"ref39","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"issue":"140","key":"ref40","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref41","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref42","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32729"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref47","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"ref49","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00787"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3306449"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","article-title":"Gpt-4v (ision) as a generalist evaluator for vision-language tasks","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00134"}],"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\/11444481.pdf?arnumber=11444481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:57Z","timestamp":1777612797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01487","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}