{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T00:29:03Z","timestamp":1716510543142},"reference-count":62,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176213","62206310","61806165"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province of China","award":["2022JQ-656"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3401031","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:30:42Z","timestamp":1715707842000},"page":"1-15","source":"Crossref","is-referenced-by-count":0,"title":["Global\u2013Local Information Soft-Alignment for Cross-Modal Remote-Sensing Image\u2013Text Retrieval"],"prefix":"10.1109","volume":"62","author":[{"given":"Gang","family":"Hu","sequence":"first","affiliation":[{"name":"Key Laboratory of Information Fusion Technology of Ministry of Education, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1258-7737","authenticated-orcid":false,"given":"Zaidao","family":"Wen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Information Fusion Technology of Ministry of Education, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2779-5099","authenticated-orcid":false,"given":"Yafei","family":"Lv","sequence":"additional","affiliation":[{"name":"Naval Research Institute of PLA, Beijing, China"}]},{"given":"Jianting","family":"Zhang","sequence":"additional","affiliation":[{"name":"Naval Research Institute of PLA, Beijing, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-5746-2677","authenticated-orcid":false,"given":"Qian","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Information and Navigation, Air Force Engineering University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2019.1585976"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2014.10.029"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2016.2598228"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2948924"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756911"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs10081243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/rs11050493"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3007533"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10182225"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs12010084"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2979273"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3216333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3021390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2968096"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220297"},{"key":"ref25","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref30","article-title":"Deep unsupervised contrastive hashing for large-scale cross-modal text-image retrieval in remote sensing","author":"Mikriukov","year":"2022","journal-title":"arXiv:2201.08125"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app13010282"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2022.2091964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883252"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref36","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref37","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref38","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019","journal-title":"arXiv:1901.06706"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref40","article-title":"A corpus for reasoning about natural language grounded in photographs","author":"Suhr","year":"2018","journal-title":"arXiv:1811.00491"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref42","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref45","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.","author":"Jia"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref47","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01594"},{"key":"ref49","first-page":"35959","article-title":"PyramidCLIP: Hierarchical feature alignment for vision-language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"ref51","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"arXiv:1508.07909"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref55","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref57","article-title":"Convolutional bypasses are better vision transformer adapters","author":"Jie","year":"2022","journal-title":"arXiv:2207.07039"},{"key":"ref58","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen"},{"key":"ref59","article-title":"Cross-modal adapter for text-video retrieval","author":"Jiang","year":"2022","journal-title":"arXiv:2211.09623"},{"key":"ref60","article-title":"UniAdapter: Unified parameter-efficient transfer learning for cross-modal modeling","author":"Lu","year":"2023","journal-title":"arXiv:2302.06605"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10530286.pdf?arnumber=10530286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T17:54:33Z","timestamp":1716486873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3401031","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}