{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T14:52:54Z","timestamp":1754146374863,"version":"3.41.2"},"reference-count":59,"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":[{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDA19020400"],"award-info":[{"award-number":["XDA19020400"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/jstars.2025.3584546","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:38:45Z","timestamp":1751290725000},"page":"16929-16941","source":"Crossref","is-referenced-by-count":0,"title":["An Improved MAE-Based Pretraining Method for Urban Public Space Monitoring With Optical Remote Sensing Imagery"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3968-8929","authenticated-orcid":false,"given":"Wentao","family":"Wei","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8302-3887","authenticated-orcid":false,"given":"Huan","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7539-5066","authenticated-orcid":false,"given":"Ping","family":"Yao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093336"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3426295"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SPACE63117.2024.10668347"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2018.1510902"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2794545"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2352\/issn.2470-1173.2016.10.robvis-392"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3514839"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"Beit: Bert pre-training of image transformers","year":"2021","author":"Bao","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3344782"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref18","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"34","author":"Xie","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"article-title":"UNIP: Rethinking pre-trained attention patterns for infrared semantic segmentation","year":"2025","author":"Zhang","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref22"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref23"},{"article-title":"Language models are unsupervised multitask learners","year":"2019","author":"Radford","key":"ref24"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3315687"},{"article-title":"Semantic image segmentation with deep convolutional nets and fully connected CRFs","year":"2014","author":"Chen","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref34","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"34","author":"Cheng","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2827308"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2789932"},{"issue":"12","key":"ref38","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.3390\/rs13081464","article-title":"Multiscale segmentation-optimized algorithm for high-spatial remote sensing imagery considering global and local optimizations","volume":"24","author":"Liang","year":"2021","journal-title":"Nat. Remote Sens. Bull."},{"volume-title":"Automatic Digital Surface Model (DSM) Generation from Linear Array Images","year":"2005","author":"Zhang","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3051053"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3207551"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183585"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/rs14091956"},{"article-title":"Special: Zero-shot hyperspectral image classification with clip","year":"2025","author":"Pang","key":"ref44"},{"article-title":"Segearth-R1: Geospatial pixel reasoning via large language model","year":"2025","author":"Li","key":"ref45"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref49","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"33","author":"Caron","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"article-title":"iBOT: Image bert pre-training with online tokenizer","year":"2021","author":"Zhou","key":"ref52"},{"article-title":"PixMIM: Rethinking pixel reconstruction in masked image modeling","year":"2023","author":"Liu","key":"ref53"},{"article-title":"SGDR: Stochastic gradient descent with warm restarts","year":"2016","author":"Loshchilov","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095835"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5194\/isprsannals-i-3-293-2012"},{"issue":"7","key":"ref59","first-page":"849","article-title":"Landscan: A global population database for estimating populations at risk","volume":"66","author":"Dobson","year":"2000","journal-title":"Photogrammetric Eng. Remote Sens."}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/10766875\/11059859.pdf?arnumber=11059859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T04:40:47Z","timestamp":1752813647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11059859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/jstars.2025.3584546","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"type":"print","value":"1939-1404"},{"type":"electronic","value":"2151-1535"}],"subject":[],"published":{"date-parts":[[2025]]}}}