{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:59Z","timestamp":1774419959510,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889818","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Textual and Visual Prompt Fusion for Image Editing via Step-Wise Alignment"],"prefix":"10.1109","author":[{"given":"Zhanbo","family":"Feng","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenan","family":"Ling","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,EIC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ci","family":"Gong","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,EIC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,EIC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wugedele","family":"Bao","sequence":"additional","affiliation":[{"name":"Hohhot Minzu College,School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert C.","family":"Qiu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,EIC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia"},{"key":"ref2","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref6","article-title":"Palm 2 technical report","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02158"},{"key":"ref8","article-title":"Multiresolution textual inversion","author":"Daras","year":"2022"},{"key":"ref9","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","author":"Bao","year":"2023"},{"key":"ref10","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01761"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref15","article-title":"Visual instruction inversion: Image editing via visual prompting","author":"Nguyen","year":"2023"},{"key":"ref16","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref18","article-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models","author":"Jia","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555436"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref24","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00585"},{"key":"ref26","article-title":"Diffusion models already have a semantic latent space","author":"Kwon","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref28","article-title":"Improved techniques for training gans","volume-title":"NeurIPS","author":"Salimans"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889818.pdf?arnumber=10889818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:38Z","timestamp":1774416338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889818","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}