{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:03:02Z","timestamp":1792688582467,"version":"4.5.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"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\/501100002347","name":"Bundesministerium f?r Bildung und Forschung","doi-asserted-by":"publisher","award":["01DD20001"],"award-info":[{"award-number":["01DD20001"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["101082130"],"award-info":[{"award-number":["101082130"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["101130544"],"award-info":[{"award-number":["101130544"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001656","name":"Helmholtz-Gemeinschaft","doi-asserted-by":"publisher","award":["ZT-I-PF-5-01"],"award-info":[{"award-number":["ZT-I-PF-5-01"]}],"id":[{"id":"10.13039\/501100001656","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3466896","type":"journal-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:26:46Z","timestamp":1729618006000},"page":"1-16","source":"Crossref","is-referenced-by-count":12,"title":["Multilabel-Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3096-6610","authenticated-orcid":false,"given":"Yi","family":"Wang","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, German Aerospace Center (DLR), Weßling, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8107-9096","authenticated-orcid":false,"given":"Xiao Xiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chair of Data Science in Earth Observation and Munich Center for Machine Learning, Technical University of Munich (TUM), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198244"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3276853"},{"key":"ref3","article-title":"On the foundations of Earth and climate foundation models","author":"Xiang Zhu","year":"2024","journal-title":"arXiv:2405.04285"},{"key":"ref4","volume-title":"ESA worldcover 10 M 2020 V100","author":"Zanaga","year":"2021"},{"key":"ref5","volume-title":"ESA worldcover 10 M 2021 V200","author":"Zanaga","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01307-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115569"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2023.3281651"},{"key":"ref11","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref13","first-page":"1","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3145854"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013967"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref24","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Cong"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref27","article-title":"SpectralGPT: Spectral remote sensing foundation model","author":"Hong","year":"2023","journal-title":"arXiv:2311.07113"},{"key":"ref28","article-title":"Feature guided masked autoencoder for self-supervised learning in remote sensing","author":"Wang","year":"2023","journal-title":"arXiv:2310.18653"},{"key":"ref29","first-page":"1","article-title":"CROMA: Remote sensing representations with contrastive radar-optical masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fuller"},{"key":"ref30","article-title":"DeCUR: Decoupling common & unique representations for multimodal self-supervision","author":"Wang","year":"2023","journal-title":"arXiv:2309.05300"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641637"},{"key":"ref32","article-title":"Neural plasticity-inspired multimodal foundation model for Earth observation","author":"Xiong","year":"2024","journal-title":"arXiv:2403.15356"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359316"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3316166"},{"key":"ref37","article-title":"Lightweight, pre-trained transformers for remote sensing timeseries","author":"Tseng","year":"2023","journal-title":"arXiv:2304.14065"},{"key":"ref38","article-title":"Foundation models for generalist geospatial artificial intelligence","author":"Jakubik","year":"2023","journal-title":"arXiv:2310.18660"},{"key":"ref39","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":"ref40","first-page":"1","article-title":"SSL4EO-L: Datasets and foundation models for Landsat imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Stewart"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref42","first-page":"8161","article-title":"Multi-label contrastive predictive coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Song"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00989"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01616"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00616"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.239"},{"key":"ref49","first-page":"472","article-title":"Self-supervised pretraining for 2D medical image segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Kalapos"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00112"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/rs14225675"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3271312"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900532"},{"key":"ref54","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref55","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01559"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01609"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref61","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3089174"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref67","volume-title":"IEEE GRSS data fusion contest","author":"Schmitt","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8518015"},{"key":"ref69","first-page":"1","article-title":"GEO-bench: Toward foundation models for earth monitoring","volume":"36","author":"Lacoste","year":"2024","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref70","article-title":"In-domain representation learning for remote sensing","author":"Neumann","year":"2019","journal-title":"arXiv:1911.06721"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.2964708"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2018863118"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113695"},{"key":"ref75","volume-title":"Fusion Competition","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref80","volume-title":"PyTorch Image Models","author":"Wightman","year":"2019"},{"key":"ref81","article-title":"BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","author":"Zaken","year":"2021","journal-title":"arXiv:2106.10199"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref83","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10726860.pdf?arnumber=10726860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:20:05Z","timestamp":1732670405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10726860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3466896","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}