{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:24:16Z","timestamp":1768073056456,"version":"3.49.0"},"reference-count":100,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Suzhou Cutting-Edge Technology Research Project","award":["SYG202335"],"award-info":[{"award-number":["SYG202335"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3417421","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T17:48:19Z","timestamp":1718992099000},"page":"1-21","source":"Crossref","is-referenced-by-count":7,"title":["Cross-Modal Contrastive Learning With Spatiotemporal Context for Correlation-Aware Multiscale Remote Sensing Image Retrieval"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-5632","authenticated-orcid":false,"given":"Lilu","family":"Zhu","sequence":"first","affiliation":[{"name":"Suzhou Aerospace Information Research Institute, Suzhou, China"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Suzhou Aerospace Information Research Institute, Suzhou, China"}]},{"given":"Yanfeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3534-6891","authenticated-orcid":false,"given":"Xiaolu","family":"Su","sequence":"additional","affiliation":[{"name":"Suzhou Aerospace Information Research Institute, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8647-9627","authenticated-orcid":false,"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"issue":"4","key":"ref1","first-page":"475","article-title":"The design of deep learning framework and model for intelligent remote sensing","volume":"51","author":"Gong","year":"2022","journal-title":"Acta Geodaetica et Cartographica Sinica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126478"},{"issue":"1","key":"ref3","first-page":"58","article-title":"Text-based, content-based, and semantic-based image retrievals: A survey","volume":"4","author":"Alkhawlani","year":"2015","journal-title":"Int. J. Comput. Inf. Technol."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3131592"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/rs13244965"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2948924"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080920"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.139"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2984703"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3236662"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.121"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3347146.3359067"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi9060354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs13142723"},{"key":"ref15","first-page":"1","article-title":"Multi-scale representation learning for spatial feature distributions using grid cells","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Mai"},{"key":"ref16","article-title":"CSP: Self-supervised contrastive spatial pre-training for geospatial-visual representations","author":"Mai","year":"2023","journal-title":"arXiv:2305.01118"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00201"},{"key":"ref18","volume-title":"The Empty Brain. Aeon","author":"Epstein","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref22","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"H\u00e9naff","year":"2019","journal-title":"arXiv:1905.09272"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","first-page":"1","article-title":"Robust pre-training by adversarial contrastive learning","volume-title":"Proc. NIPS","author":"Jiang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482332"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/rs10010007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2018.1508907"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/394\/5\/052021"},{"issue":"6","key":"ref31","first-page":"199","article-title":"A multidimensional retrieval strategy for massive spatio-temporal data","volume":"45","author":"Zhao","year":"2020","journal-title":"Sci. Surv. Mapp."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLII-3-W10-653-2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2020.102765"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1108\/SR-04-2019-0092"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13670-w"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2021.1966119"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2019.1647368"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2961634"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2980870"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2205158"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5220\/0001787803310340"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756911"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3035676"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3007533"},{"key":"ref45","first-page":"86","article-title":"Remote sensing image retrieval based on DenseNet model and CBAM","volume-title":"Proc. IEEE 3rd Int. Conf. Comput. Commun. Eng. Technol. (CCET)","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3136159"},{"key":"ref47","first-page":"1512","article-title":"Supervised contrastive learning-based deep hash retrieval for remote sensing image","volume-title":"Proc. IEEE Int. Geosci. Remote Sens. Symp.","author":"Huang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3275644"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/int.23082"},{"key":"ref50","volume-title":"Tutorial 2.3.1\u2014SpatiaLite GIS User Manual","year":"2024"},{"key":"ref51","volume-title":"Indexing","year":"2024"},{"key":"ref52","volume-title":"Build Indexes"},{"issue":"7","key":"ref53","first-page":"78","article-title":"Research on retrieval of remote sensing data service system based on PostGIS","volume":"44","author":"Chen","year":"2021","journal-title":"Geomatics Spatial Geogr. Inf."},{"key":"ref54","volume-title":"Index Types\u2014Geospatial Indexes","year":"2024"},{"key":"ref55","first-page":"63","article-title":"Research on GeoServer tile caching mechanism","author":"Yang","year":"2011","journal-title":"Netw. Secur. Technol. Appl."},{"key":"ref56","volume-title":"GeoMesa Data Stores-GeoMesa5.0.0 User Manual","year":"2024"},{"key":"ref57","volume-title":"Core Concepts\u2014GeoTrellis 3.6.0 Documentation","year":"2024"},{"key":"ref58","volume-title":"LocationTech, GeoWave Overview","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref60","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref61","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref65","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. NIPS","author":"Lu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref67","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (PMLR)","author":"Jia"},{"key":"ref68","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28559"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.819"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10281814"},{"key":"ref72","article-title":"Text2Seg: Remote sensing image semantic segmentation via text-guided visual foundation models","author":"Zhang","year":"2023","journal-title":"arXiv:2304.10597"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3228518"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/app132212462"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126623502213"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3231851"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3280546"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3194732"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3390\/rs15051187"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3192460"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"ref84","article-title":"RSGPT: A remote sensing vision language model and benchmark","author":"Hu","year":"2023","journal-title":"arXiv:2307.15266"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref88","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref90","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref91","article-title":"Making pre-trained language models better few-shot learners","author":"Gao","year":"2020","journal-title":"arXiv:2012.15723"},{"key":"ref92","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"arXiv:2107.07651"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3115569"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref98","volume-title":"Living Atlas of the World","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.007"},{"key":"ref100","volume-title":"The Stress Testing Tool","year":"2023"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10568105.pdf?arnumber=10568105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T05:00:05Z","timestamp":1720587605000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10568105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3417421","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}