{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:03:05Z","timestamp":1776441785374,"version":"3.51.2"},"reference-count":64,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072218"],"award-info":[{"award-number":["62072218"]}],"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":["61862030"],"award-info":[{"award-number":["61862030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2023.3320954","type":"journal-article","created":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T17:42:22Z","timestamp":1696009342000},"page":"1-15","source":"Crossref","is-referenced-by-count":11,"title":["STCP: Synergistic Transformer and Convolutional Neural Network for Pansharpening"],"prefix":"10.1109","volume":"61","author":[{"given":"Zhao","family":"Su","sequence":"first","affiliation":[{"name":"School of Information Technology, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9467-0942","authenticated-orcid":false,"given":"Yong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tiangong University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2771-8461","authenticated-orcid":false,"given":"Shuying","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Software, Tiangong University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3537-979X","authenticated-orcid":false,"given":"Weiguo","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Software and Internet of Things Engineering, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9375-8918","authenticated-orcid":false,"given":"Jiancheng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Software and Internet of Things Engineering, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2673-2192","authenticated-orcid":false,"given":"Wei","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Jiangxi Science and Technology Normal University, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7216-427X","authenticated-orcid":false,"given":"Changjie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Technology, Jiangxi University of Finance and Economics, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.04.001"},{"key":"ref57","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2015.7325690"},{"key":"ref56","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3247165"},{"key":"ref59","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2819501"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183468"},{"key":"ref52","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijleo.2013.10.064"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2006.02.001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2736020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs8070594"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031366"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2794888"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00097"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref45","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"wu","year":"2020","journal-title":"arXiv 2006 03677"},{"key":"ref48","article-title":"DsTer: A dense spectral transformer for remote sensing spectral super-resolution","volume":"109","author":"he","year":"2022","journal-title":"Int J Appl Earth Observ Geoinf"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102731"},{"key":"ref42","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn (ICML)"},{"key":"ref41","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020","journal-title":"arXiv 2010 04159"},{"key":"ref44","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020","journal-title":"arXiv 2012 12877"},{"key":"ref43","article-title":"TransGAN: Two transformers can make one strong GAN","author":"jiang","year":"2021","journal-title":"arXiv 2102 07074"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109061"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2007.901007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S1566-2535(01)00036-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.14358\/PERS.72.5.591"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/rs10081238"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2361734"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3187025"},{"key":"ref40","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096538"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152425"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3232189"},{"key":"ref31","first-page":"1","article-title":"An image is worth 16?16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref30","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3199210"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2930982"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3088865"},{"key":"ref39","article-title":"Toward transformer-based object detection","author":"beal","year":"2020","journal-title":"arXiv 2012 09958"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3179473"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3098752"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01051"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010441"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"ref63","first-page":"691","article-title":"Fusion of satellite images of different spatial resolutions: Assessing the quality of resulting images","volume":"63","author":"wald","year":"1997","journal-title":"Photogramm Eng Remote Sens"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250621"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3241643"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","volume":"2017","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20267"},{"key":"ref29","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol (NAACL-HLT)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10268029.pdf?arnumber=10268029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T18:59:23Z","timestamp":1699469963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10268029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3320954","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}