{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:42:22Z","timestamp":1779385342742,"version":"3.53.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3015404"],"award-info":[{"award-number":["2024YFC3015404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42271446"],"award-info":[{"award-number":["42271446"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004829","name":"Central Guidance for Local Science and Technology Development Fund Projects of Sichuan Province","doi-asserted-by":"publisher","award":["2024ZYD0084"],"award-info":[{"award-number":["2024ZYD0084"]}],"id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3542868","type":"journal-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:18:47Z","timestamp":1740082727000},"page":"1-15","source":"Crossref","is-referenced-by-count":10,"title":["Tuple Perturbation-Based Contrastive Learning Framework for Multimodal Remote Sensing Image Semantic Segmentation"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-6722","authenticated-orcid":false,"given":"Yuanxin","family":"Ye","sequence":"first","affiliation":[{"name":"Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinkun","family":"Dai","sequence":"additional","affiliation":[{"name":"Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3471-9924","authenticated-orcid":false,"given":"Liang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyi","family":"Duan","sequence":"additional","affiliation":[{"name":"Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5243-7189","authenticated-orcid":false,"given":"Ran","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, 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, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3212-9584","authenticated-orcid":false,"given":"Danfeng","family":"Hong","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/01431160412331291297"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3362475"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130716"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2023.113856","article-title":"Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networks","volume":"299","author":"Hong","year":"2023","journal-title":"Remote Sens. Environ."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3279834"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878958"},{"key":"ref8","volume-title":"Manual of Remote Sensing, Remote Sensing for Natural Resource Management and Environmental Monitoring","author":"Ustin","year":"2004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3167644"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3295797"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3286826","article-title":"Multimodal fusion transformer for remote sensing image classification","volume":"61","author":"Roy","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2975252"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124913"},{"key":"ref14","article-title":"Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks","author":"Audebert","year":"2017","journal-title":"arXiv:1711.08681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1117\/12.2587991"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.isprsjprs.2024.01.022","article-title":"HD-Net: High-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition","volume":"209","author":"Li","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"ref18","article-title":"MCANet: A joint semantic segmentation framework of optical and SAR images for land use classification","volume":"106","author":"Li","year":"2022","journal-title":"Int. J. Appl. Earth Observ. Geoinf."},{"key":"ref19","first-page":"801","article-title":"Encoder\u2013decoder with atrous separable convolution for semantic image segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102830"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.104241"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref24","article-title":"Prototypical contrastive learning of unsupervised representations","author":"Li","year":"2021","journal-title":"arXiv:2005.04966"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00129"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3128072"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3034133"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3038420"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3069799"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01525"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109345"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00079"},{"issue":"11","key":"ref34","doi-asserted-by":"crossref","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","article-title":"Self-supervised visual feature learning with deep neural networks: A survey","volume":"43","author":"Jing","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3202036"},{"key":"ref37","article-title":"The QXS-SAROPT dataset for deep learning in SAR-optical data fusion","author":"Huang","year":"2021","journal-title":"arXiv:2103.08259"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref40","first-page":"1","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2020.104042","article-title":"Deep multimodal fusion for semantic image segmentation: A survey","volume":"105","author":"Zhang","year":"2021","journal-title":"Image Vis. Comput."},{"issue":"1","key":"ref43","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","article-title":"Multisensor data fusion: A review of the state-of-the-art","volume":"14","author":"Khaleghi","year":"2013","journal-title":"Inf. Fusion"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.isprsjprs.2021.12.007","article-title":"CMGFNet: A deep cross-modal gated fusion network for building extraction from very high-resolution remote sensing images","volume":"184","author":"Hosseinpour","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref46","article-title":"A dual-stream high resolution network: Deep fusion of GF-2 and GF-3 data for land cover classification","volume":"112","author":"Ren","year":"2022","journal-title":"Int. J. Appl. Earth Observ. Geoinf."},{"key":"ref47","first-page":"1800","article-title":"Xception: Deep learning with depthwise separable convolutions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Chollet"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3351874"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3353259"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3367948"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3147513"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10896945.pdf?arnumber=10896945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:39:27Z","timestamp":1741372767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10896945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3542868","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}