{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:45:21Z","timestamp":1767084321700,"version":"3.37.3"},"reference-count":56,"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":[{"name":"German Federal Ministry for Economic Affairs and Climate Action","award":["50EE2201C"],"award-info":[{"award-number":["50EE2201C"]}]},{"name":"German Federal Ministry of Education and Research","award":["01DD20001"],"award-info":[{"award-number":["01DD20001"]}]},{"DOI":"10.13039\/501100013549","name":"Bundesministerium f?r Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz","doi-asserted-by":"publisher","award":["67KI32002B"],"award-info":[{"award-number":["67KI32002B"]}],"id":[{"id":"10.13039\/501100013549","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.2024.3412629","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T17:32:14Z","timestamp":1721323934000},"page":"1-12","source":"Crossref","is-referenced-by-count":7,"title":["Self-Supervised Pretraining With Monocular Height Estimation for Semantic Segmentation"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3953-585X","authenticated-orcid":false,"given":"Zhitong","family":"Xiong","sequence":"first","affiliation":[{"name":"Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sining","family":"Chen","sequence":"additional","affiliation":[{"name":"Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilei","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Engineering and Design, Technical University of Munich (TUM), Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2017.2762307"},{"key":"ref2","article-title":"EarthNets: Empowering AI in Earth observation","author":"Xiong","year":"2022","journal-title":"arXiv:2210.04936"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3311764"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2019.2893783"},{"key":"ref5","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"2","author":"Eigen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.238"},{"key":"ref8","article-title":"IM2HEIGHT: Height estimation from single monocular imagery via fully residual convolutional-deconvolutional network","author":"Mou","year":"2018","journal-title":"arXiv:1802.10249"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01452"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00127"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.isprsjprs.2021.11.024","article-title":"Large-scale building height retrieval from single SAR imagery based on bounding box regression networks","volume":"184","author":"Sun","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2976199"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref14","article-title":"This looks like that: Deep learning for interpretable image recognition","author":"Chen","year":"2018","journal-title":"arXiv:1806.10574"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00613"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00397"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01264"},{"key":"ref19","article-title":"On the foundations of Earth and climate foundation models","author":"Xiang Zhu","year":"2024","journal-title":"arXiv:2405.04285"},{"key":"ref20","article-title":"Neural plasticity-inspired foundation model for observing the Earth crossing modalities","author":"Xiong","year":"2024","journal-title":"arXiv:2403.15356"},{"key":"ref21","first-page":"5506","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":"ref22","article-title":"DeCUR: Decoupling common & unique representations for multimodal self-supervision","author":"Wang","year":"2023","journal-title":"arXiv:2309.05300"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_27"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_37"},{"key":"ref25","article-title":"Exploring self-attention for crop-type classification explainability","author":"Obadic","year":"2022","journal-title":"arXiv:2210.13167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/make5010010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00908"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8128167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2806945"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8899861"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3321255"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00148"},{"key":"ref39","article-title":"SpectralGPT: Spectral remote sensing foundation model","author":"Hong","year":"2023","journal-title":"arXiv:2311.07113"},{"article-title":"On the importance of single directions for generalization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Morcos","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"ref43","article-title":"Data fusion contest 2019 (DFC2019)","author":"Le Saux","year":"2019","journal-title":"IEEE DataPort"},{"volume-title":"Grand Theft Auto V","year":"2021","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"volume-title":"MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark","year":"2020","author":"Contributors","key":"ref46"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov","key":"ref47"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref51","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18084278"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2021.112844"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10604292.pdf?arnumber=10604292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T04:43:23Z","timestamp":1721709803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10604292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3412629","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"type":"print","value":"0196-2892"},{"type":"electronic","value":"1558-0644"}],"subject":[],"published":{"date-parts":[[2024]]}}}