{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:20:03Z","timestamp":1792790403591,"version":"4.5.0"},"reference-count":60,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f?r Bildung und Forschung","doi-asserted-by":"publisher","award":["in the framework of the international future AI la"],"award-info":[{"award-number":["in the framework of the international future AI la"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023863","name":"Munich Center for Machine Learning","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023863","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["EvoLand\/101082130"],"award-info":[{"award-number":["EvoLand\/101082130"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023371","name":"Helmholtz Artificial Intelligence Cooperation Unit","doi-asserted-by":"publisher","award":["ZT-I-PF-5-01 ? Local Unit Munich Unit @Aeronauti"],"award-info":[{"award-number":["ZT-I-PF-5-01 ? Local Unit Munich Unit @Aeronauti"]}],"id":[{"id":"10.13039\/501100023371","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.2025.3552642","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T17:36:31Z","timestamp":1742319391000},"page":"1-17","source":"Crossref","is-referenced-by-count":7,"title":["CromSS: Cross-Modal Pretraining With Noisy Labels for Remote Sensing Image Segmentation"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9172-3586","authenticated-orcid":false,"given":"Chenying","family":"Liu","sequence":"first","affiliation":[{"name":"Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2422-7289","authenticated-orcid":false,"given":"Conrad M.","family":"Albrecht","sequence":"additional","affiliation":[{"name":"Remote Sensing Technology Institute, DLR, Weßling, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3096-6610","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Chair of Data Science in Earth Observation, TUM, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8107-9096","authenticated-orcid":false,"given":"Xiao","family":"Xiang Zhu","sequence":"additional","affiliation":[{"name":"Chair of Data Science in Earth Observation, TUM, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"5","key":"ref1","article-title":"Artificial intelligence for geoscience: Progress, challenges and perspectives","volume":"5","author":"Zhao","year":"2024","journal-title":"Innovation"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.isprsjprs.2021.02.009","article-title":"Learning deep semantic segmentation network under multiple weakly-supervised constraints for cross-domain remote sensing image semantic segmentation","volume":"175","author":"Li","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"issue":"4","key":"ref3","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1109\/MGRS.2022.3198244","article-title":"Self-supervised learning in remote sensing: A review","volume":"10","author":"Wang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref4","article-title":"On the foundations of Earth and climate foundation models","author":"Zhu","year":"2024","journal-title":"arXiv:2405.04285"},{"key":"ref5","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"He"},{"key":"ref6","first-page":"9630","article-title":"Emerging properties in self-supervised vision transformers","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Caron"},{"key":"ref7","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref9","article-title":"RingMo: A remote sensing foundation model with masked image modeling","volume":"61","author":"Sun","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref10","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cong"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02627"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref13","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"He"},{"key":"ref14","first-page":"10181","article-title":"Geography-aware self-supervised learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Ayush"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00928"},{"key":"ref16","article-title":"Extending global-local view alignment for self-supervised learning with remote sensing imagery","author":"Wanyan","year":"2023","journal-title":"arXiv:2303.06670"},{"key":"ref17","first-page":"5261","article-title":"Change-aware sampling and contrastive learning for satellite images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Mall"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MGRS.2023.3281651","article-title":"SSL4EO-s12: A large-scale multimodal, multitemporal dataset for self-supervised learning in Earth observation [software and data sets]","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref19","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Deng"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Ravi"},{"key":"ref22","article-title":"Large foundation model empowered discriminative underwater image enhancement","volume":"63","author":"Wang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3373908"},{"key":"ref25","first-page":"181","article-title":"Exploring the limits of weakly supervised pretraining","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Mahajan"},{"key":"ref26","first-page":"12038","article-title":"Large-scale weakly-supervised pre-training for video action recognition","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Ghadiyaram"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2719738"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2612821"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641089"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.isprsjprs.2024.12.002","article-title":"Underwater image captioning: Challenges, models, and datasets","volume":"220","author":"Li","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3173811","article-title":"From easy to hard: Learning language-guided curriculum for visual question answering on remote sensing data","volume":"60","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2016.2561021"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.isprsjprs.2021.05.011","article-title":"Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning model","volume":"178","author":"Hong","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref34","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.isprsjprs.2022.03.012","article-title":"Multi-modal temporal attention models for crop mapping from satellite time series","volume":"187","author":"Garnot","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref35","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.isprsjprs.2023.09.021","article-title":"Improving agricultural field parcel delineation with a dual branch spatiotemporal fusion network by integrating multimodal satellite data","volume":"205","author":"Cai","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref36","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.isprsjprs.2024.01.002","article-title":"Similarity and dissimilarity relationships based graphs for multimodal change detection","volume":"208","author":"Sun","year":"2024","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref37","first-page":"5506","article-title":"CROMA: Remote sensing representations with contrastive radar-optical masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fuller"},{"key":"ref38","article-title":"SkySense: A multi-modal remote sensing foundation model towards universal interpretation for Earth observation imagery","author":"Guo","year":"2023","journal-title":"arXiv:2312.10115"},{"key":"ref39","article-title":"Decoupling common and unique representations for multimodal self-supervised learning","author":"Wang","year":"2023","journal-title":"arXiv:2309. 05300"},{"key":"ref40","article-title":"Neural plasticity-inspired multimodal foundation model for Earth observation","author":"Xiong","year":"2024","journal-title":"arXiv:2403.15356"},{"key":"ref41","article-title":"Self-supervised SAR-optical data fusion of Sentinel-1\/-2 images","volume":"60","author":"Chen","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref42","article-title":"A co-learning method to utilize optical images and photogrammetric point clouds for building extraction","volume":"116","author":"Xie","year":"2023","journal-title":"Int. J. Appl. Earth Observ. Geoinf."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9433790"},{"key":"ref44","first-page":"960","article-title":"Decoupling \u2019when to update\u2019 from \u2019how to update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Malach"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"1","key":"ref47","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1038\/s41597-022-01307-4","article-title":"Dynamic World, near real-time global 10 M land use land cover mapping","volume":"9","author":"Brown","year":"2022","journal-title":"Sci. Data"},{"key":"ref48","article-title":"2020 IEEE GRSS data fusion contest","author":"Schmitt","year":"2019","journal-title":"IEEE Dataport"},{"key":"ref49","volume-title":"LUCAS 2015 Topsoil Survey: Presentation of Dataset and Results","author":"Jones","year":"2020"},{"key":"ref50","first-page":"206","article-title":"Open land cover from OpenStreetMap and remote sensing","volume":"63","author":"Schultz","year":"2017","journal-title":"Int. J. Appl. Earth Observ. Geoinf."},{"key":"ref51","volume-title":"CORINE Land Cover","year":"2024"},{"key":"ref52","first-page":"1","article-title":"A survey of loss functions for semantic segmentation","volume-title":"Proc. IEEE Conf. Comput. Intell. Bioinf. Comput. Biol. (CIBCB)","author":"Jadon"},{"key":"ref53","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Szegedy"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10930953.pdf?arnumber=10930953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T07:29:07Z","timestamp":1743838147000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10930953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3552642","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}