{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T09:14:17Z","timestamp":1783674857782,"version":"3.55.0"},"reference-count":61,"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\/501100004829","name":"Department of Science and Technology of Sichuan Province","doi-asserted-by":"publisher","award":["2025YFNH0001"],"award-info":[{"award-number":["2025YFNH0001"]}],"id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["12271083"],"award-info":[{"award-number":["12271083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005408","name":"University of Electronic Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005408","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\/iccv51701.2025.01092","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11744-11754","source":"Crossref","is-referenced-by-count":1,"title":["MMAIF: Multi-Task and Multi-Degradation All-in-One for Image Fusion with Language Guidance"],"prefix":"10.1109","author":[{"given":"Zihan","family":"Cao","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China (UESTC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China (UESTC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China (UESTC)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang-Jian","family":"Deng","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China (UESTC)"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2794218"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0067"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102158"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680905"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_2"},{"issue":"70","key":"ref6","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","article-title":"Flow matching in latent space","author":"Dao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International Conference on machine learning","author":"Dauphin"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3244750"},{"key":"ref10","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","article-title":"NVIDIA et. al. Cosmos world foundation model platform for physical ai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611758"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref20","article-title":"Cautious optimizers: Improving training with one line of code","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_41"},{"key":"ref22","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"I2 SB: Image-to-image schr\u00f6dinger bridge","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.013"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Controlling vision-language models for multi-task image restoration","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.02.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref35","article-title":"Promptir: Prompting for all-in-one blind image restoration. arxiv 2023","author":"Potlapalli","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681064"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234340"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102414"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3523364"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02552"},{"key":"ref49","article-title":"Text-difuse: An interactive multi-modal image fusion framework based on textmodulated diffusion model","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.08.002"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.005"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261282"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296874"},{"key":"ref55","article-title":"Image and video tokenization with binary spherical quantization","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02448"},{"key":"ref59","article-title":"Image fusion via vision-language model","author":"Zhao","year":"2024","journal-title":"IMCL"},{"key":"ref60","first-page":"77962","article-title":"Ssdiff: Spatial-spectral integrated diffusion model for remote sensing pansharpening","volume":"37","author":"Zhong","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref61","article-title":"Value residual learning for alleviating attention concentration in transformers","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00678"},{"key":"ref63","article-title":"Designing a better asymmetric vqgan for stablediffusion","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"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\/11446182.pdf?arnumber=11446182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:20:13Z","timestamp":1777612813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01092","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}