{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T14:16:03Z","timestamp":1774188963188,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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","award":["U23B2009"],"award-info":[{"award-number":["U23B2009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471158"],"award-info":[{"award-number":["62471158"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3642842","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:45:23Z","timestamp":1765478723000},"page":"3970-3987","source":"Crossref","is-referenced-by-count":0,"title":["Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4267-6897","authenticated-orcid":false,"given":"Jiayang","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"given":"Chengjie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0173-1385","authenticated-orcid":false,"given":"Pengwei","family":"Liang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3264-3265","authenticated-orcid":false,"given":"Jiayi","family":"Ma","sequence":"additional","affiliation":[{"name":"Electronic Information School, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01663"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48765-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888684"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3399119"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02552"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3568433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124878"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103148"},{"key":"ref13","article-title":"ControlFusion: A controllable image fusion network with language-vision degradation prompts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2977573"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.12.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"ref18","first-page":"60749","article-title":"Image fusion via vision-language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3541562"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3351933"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012548"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.06.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s20082169"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3069339"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3075747"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475299"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2887342"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2997127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00572"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3583132"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102839"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00745"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547902"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01341"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101870"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01666"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00213"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680971"},{"key":"ref44","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.07.011"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6975"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_41"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_41"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102655"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102450"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1658"},{"key":"ref54","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref56","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Xie","year":"2025"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"ref59","article-title":"TransFusion: Predict the next token and diffuse images with one multi-modal model","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Zhou","year":"2025"},{"key":"ref60","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref61","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref62","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.007"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1117\/1.OE.51.1.010901"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6936"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078906"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.08.002"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2794218"},{"key":"ref70","first-page":"39552","article-title":"Text-DiFuse: An interactive multi-modal image fusion framework based on text-modulated diffusion model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Zhang","year":"2025"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.014"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28413"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102790"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3823"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11297852.pdf?arnumber=11297852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:55Z","timestamp":1773106495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11297852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":75,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3642842","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}