{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:26:17Z","timestamp":1784399177714,"version":"3.55.0"},"reference-count":65,"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":"Guangdong Provincial Key Laboratory of Future Networks of Intelligence","award":["2022B1212010001"],"award-info":[{"award-number":["2022B1212010001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42371374"],"award-info":[{"award-number":["42371374"]}],"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":["41801323"],"award-info":[{"award-number":["41801323"]}],"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":[[2024]]},"DOI":"10.1109\/tgrs.2024.3373033","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T19:17:09Z","timestamp":1709839029000},"page":"1-15","source":"Crossref","is-referenced-by-count":221,"title":["A Multilevel Multimodal Fusion Transformer for Remote Sensing Semantic Segmentation"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2180-2964","authenticated-orcid":false,"given":"Xianping","family":"Ma","sequence":"first","affiliation":[{"name":"School of Science and Engineering, the Future Network of Intelligence Institute (FNii), The Chinese University of Hong Kong (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6127-4801","authenticated-orcid":false,"given":"Xiaokang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3316-5381","authenticated-orcid":false,"given":"Man-On","family":"Pun","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, the Future Network of Intelligence Institute (FNii), The Chinese University of Hong Kong (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"MizarVision, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2933747"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172183"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.02.013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/rs13010090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/rs14081912"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2363477"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2381272"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.08.014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.08.011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2015.2442594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2014.2341044"},{"key":"ref13","first-page":"1","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Kr\u00e4henb\u00fchl"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54181-5_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.11.011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124913"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.05.011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3165005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3244136"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3119654"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3240982"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.01.018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3243042"},{"key":"ref26","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3157721"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561675"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102926"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3017414"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3286826"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.11.009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2913861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref43","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Sys. (NIPS)","volume":"34","author":"Xie"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3178991"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.007"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"ref49","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Ngiam"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245324"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3159032"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3241648"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105686"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/rs14051294"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/math11030722"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3063381"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10458980.pdf?arnumber=10458980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:00:16Z","timestamp":1725249616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10458980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3373033","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}