{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:30:01Z","timestamp":1771698601781,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62322117"],"award-info":[{"award-number":["62322117"]}],"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":["62371365"],"award-info":[{"award-number":["62371365"]}],"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":["62121001"],"award-info":[{"award-number":["62121001"]}],"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":["62071360"],"award-info":[{"award-number":["62071360"]}],"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":["U24B20136"],"award-info":[{"award-number":["U24B20136"]}],"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":["U22B2014"],"award-info":[{"award-number":["U22B2014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFE0208100"],"award-info":[{"award-number":["2023YFE0208100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Fund of Xidian University","award":["YJSJ25007"],"award-info":[{"award-number":["YJSJ25007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcsvt.2025.3549750","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T13:48:34Z","timestamp":1741700914000},"page":"7605-7617","source":"Crossref","is-referenced-by-count":11,"title":["M\u00b3amba: CLIP-Driven Mamba Model for Multi-Modal Remote Sensing Classification"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1892-3645","authenticated-orcid":false,"given":"Mingxiang","family":"Cao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8310-024X","authenticated-orcid":false,"given":"Weiying","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6455-047X","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3111-1116","authenticated-orcid":false,"given":"Jiaqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9921-2043","authenticated-orcid":false,"given":"Kai","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0851-6565","authenticated-orcid":false,"given":"Jie","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0234-6270","authenticated-orcid":false,"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296745"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407131"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3322470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28710"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102560"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3037734"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"ref13","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref15","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Riquelme"},{"key":"ref16","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref20","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"key":"ref21","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02207"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref29","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. IEEE\/CVF Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3234124"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3233726"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3286826"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.12.020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3406690"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3375511"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3274545"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268757"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3525734"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3102-9"},{"key":"ref42","article-title":"SpectralMamba: Efficient mamba for hyperspectral image classification","author":"Yao","year":"2024","journal-title":"arXiv:2404.08489"},{"key":"ref43","article-title":"S2 mamba: A spatial\u2013spectral state space model for hyperspectral image classification","author":"Wang","year":"2024","journal-title":"arXiv:2404.18213"},{"key":"ref44","article-title":"Mamba-in-mamba: Centralized mamba-cross-scan in tokenized mamba model for hyperspectral image classification","author":"Zhou","year":"2024","journal-title":"arXiv:2405.12003"},{"key":"ref45","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2014.2305441"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.05.011"},{"key":"ref49","article-title":"MUUFL Gulfport hyperspectral and LiDAR airborne data set","author":"Gader","year":"2013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3232498"},{"key":"ref51","first-page":"25697","article-title":"Semi-supervised vision transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Cai"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3284671"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11114024\/10919126.pdf?arnumber=10919126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:02:18Z","timestamp":1754503338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10919126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":52,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3549750","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}