{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:20:47Z","timestamp":1778948447319,"version":"3.51.4"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["2022ZD0118402"],"award-info":[{"award-number":["2022ZD0118402"]}],"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":["62171436"],"award-info":[{"award-number":["62171436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201550"],"award-info":[{"award-number":["62201550"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306302"],"award-info":[{"award-number":["62306302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2023.3316166","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:53:23Z","timestamp":1695059603000},"page":"1-21","source":"Crossref","is-referenced-by-count":44,"title":["RingMo-Sense: Remote Sensing Foundation Model for Spatiotemporal Prediction via Spatiotemporal Evolution Disentangling"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4187-9755","authenticated-orcid":false,"given":"Fanglong","family":"Yao","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4612-508X","authenticated-orcid":false,"given":"Wanxuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7542-0790","authenticated-orcid":false,"given":"Heming","family":"Yang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0847-6594","authenticated-orcid":false,"given":"Liangyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0934-8161","authenticated-orcid":false,"given":"Chenglong","family":"Liu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4850-7678","authenticated-orcid":false,"given":"Leiyi","family":"Hu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8138-1372","authenticated-orcid":false,"given":"Hongfeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nayu","family":"Liu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3469-5624","authenticated-orcid":false,"given":"Chubo","family":"Deng","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deke","family":"Tang","sequence":"additional","affiliation":[{"name":"China Geovis Earth Hefei Company Ltd., Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changshuo","family":"Chen","sequence":"additional","affiliation":[{"name":"China Geovis Technology Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7864-7254","authenticated-orcid":false,"given":"Jiaqi","family":"Yu","sequence":"additional","affiliation":[{"name":"China Geovis Environment Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","first-page":"12","article-title":"A dataset for infrared image dim-small aircraft target detection and tracking under ground\/air background","volume":"5","author":"hui","year":"2020","journal-title":"Sci China D"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3140809"},{"key":"ref59","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00374"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"ref52","first-page":"4576","article-title":"Joint inference of groups, events and human roles in aerial videos","author":"shu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref55","first-page":"9186","article-title":"WebUAV-3M: A benchmark for unveiling the power of million-scale deep UAV tracking","volume":"45","author":"zhang","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"ref51","article-title":"Detecting and tracking small and dense moving objects in satellite videos: A benchmark","volume":"60","author":"yin","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.267"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3181279"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196845"},{"key":"ref42","article-title":"Deep learning for precipitation nowcasting: A benchmark and a new model","volume":"30","author":"shi","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01518"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3062936"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.3005751"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref7","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"Proc ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2016.2619984"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3174239"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/atmos8030048"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref34","article-title":"RingMo: A remote sensing foundation model with masked image modeling","volume":"61","author":"sun","year":"2022","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref37","article-title":"Seasonal contrast: Unsupervised pre-training from uncurated remote sensing data","author":"ma\u00f1as","year":"2021","journal-title":"arXiv 2103 16607"},{"key":"ref36","article-title":"Geographical knowledge-driven representation learning for remote sensing images","author":"li","year":"2021","journal-title":"arXiv 2107 05276"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref30","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109345"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0450(1995)034<1286:NOMAGO>2.0.CO;2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0426(1993)010<0785:TTITAA>2.0.CO;2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3693-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3609-4"},{"key":"ref26","article-title":"An image is worth 16&#x00D7;16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref25","article-title":"InternImage: Exploring large-scale vision foundation models with deformable convolutions","author":"wang","year":"2022","journal-title":"arXiv 2211 05778"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3169773"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3233847"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3663-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref27","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020","journal-title":"arXiv 2003 04297"},{"key":"ref29","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01366"},{"key":"ref14","article-title":"Learning video representations using contrastive bidirectional transformer","author":"sun","year":"2019","journal-title":"arXiv 1906 05743"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref10","article-title":"MaskVIT: Masked visual pre-training for video prediction","author":"gupta","year":"2022","journal-title":"arXiv 2206 11894"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3588-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref92","article-title":"MOT16: A benchmark for multi-object tracking","author":"milan","year":"2016","journal-title":"arXiv 1603 00831 [cs]"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486597"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.104"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00247"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00485"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3124222"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_42"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152250"},{"key":"ref83","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"ge","year":"2021","journal-title":"arXiv 2107 08430"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00815"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3242147"},{"key":"ref74","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume":"29","author":"dai","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3198083"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3087835"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3172785"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3198851"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3159530"},{"key":"ref73","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref72","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"shi","year":"2015","journal-title":"arXiv 1506 04214"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3193458"},{"key":"ref67","first-page":"180","article-title":"Deep learning prediction of incoming rainfalls: An operational service for the city","author":"song","year":"2019","journal-title":"Proc Int Conf Data Mining Workshops (ICDMW)"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054232"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413934"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"ref65","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2017","journal-title":"arXiv 1412 6980"},{"key":"ref60","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01356"},{"key":"ref61","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2015","journal-title":"arXiv 1511 05440"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10254320.pdf?arnumber=10254320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:08:49Z","timestamp":1698084529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10254320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3316166","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}