{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T20:46:25Z","timestamp":1782506785126,"version":"3.54.5"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62471040"],"award-info":[{"award-number":["62471040"]}],"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":["W2411055"],"award-info":[{"award-number":["W2411055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3702423","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:13:16Z","timestamp":1781813596000},"page":"6674-6685","source":"Crossref","is-referenced-by-count":0,"title":["LiteMFT: Lightweight Multi-Modal Fine-Tuning for Semantic Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1276-5936","authenticated-orcid":false,"given":"Chengwang","family":"Guo","sequence":"first","affiliation":[{"name":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Geography, Jockey Club STEM Laboratory of Quantitative Remote Sensing, The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5724-9785","authenticated-orcid":false,"given":"Mengmeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4642-4485","authenticated-orcid":false,"given":"Huan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7015-7335","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Electronics and the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01633"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-017-0141-z"},{"key":"ref4","article-title":"Robust hierarchical scene graph generation","volume-title":"Proc. NeurIPS Workshop, New Frontiers Graph Learn.","author":"Zhang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02667"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3349072"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02630"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247999"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00298"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO54168.2021.9739390"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.107123"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3204345"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208833"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"ref20","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref21","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1364\/OE.416130"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.12.009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211086"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32743"},{"key":"ref30","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref31","article-title":"MAGIC++: Efficient and resilient modality-agnostic semantic segmentation via hierarchical modality selection","author":"Zheng","year":"2024","journal-title":"arXiv:2412.16876"},{"key":"ref32","article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01802"},{"key":"ref34","first-page":"21753","article-title":"GeminiFusion: Efficient pixel-wise multimodal fusion for vision transformer","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Jia"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01948"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00401"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3535896"},{"issue":"2","key":"ref39","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","volume":"1","author":"Hu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206396"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196831"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2021.102638"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3060707"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2904733"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3164899"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127913"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27981"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01188-y"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.533"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2004.831865"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2381602"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756851"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2725580"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3097093"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3171572"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007457"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref63","first-page":"1","article-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref64","article-title":"DoRA: Weight-decomposed low-rank adaptation","author":"Liu","year":"2024","journal-title":"arXiv:2402.09353"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref67","first-page":"1","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11570804.pdf?arnumber=11570804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T19:48:01Z","timestamp":1782503281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11570804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3702423","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}