{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:34:40Z","timestamp":1777894480417,"version":"3.51.4"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST ASPIRE","award":["JPMJAP2326"],"award-info":[{"award-number":["JPMJAP2326"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/jstars.2025.3637891","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:58:13Z","timestamp":1764269893000},"page":"1691-1702","source":"Crossref","is-referenced-by-count":1,"title":["Dual-Stream Multimodal Fusion With Local\u2013Global Attention for Remote-Sensing Object Detection"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0837-139X","authenticated-orcid":false,"given":"Youxiang","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Information and Computer Science, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8873-1544","authenticated-orcid":false,"given":"Zhuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Science, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8596-1227","authenticated-orcid":false,"given":"Tiantian","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3961-1426","authenticated-orcid":false,"given":"Tomoaki","family":"Ohtsuki","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Science, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3888-2881","authenticated-orcid":false,"given":"Guan","family":"Gui","sequence":"additional","affiliation":[{"name":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref3","article-title":"xView: Objects in context in overhead imagery","author":"Lam"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3198577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3360456"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2953936"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3128060"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3235002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2953119"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3643453"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3219341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3288143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3387837"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3243036"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124913"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"ref17","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3388013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3041316"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3258666"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3428346"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3386735"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3446814"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2024.3441019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs15235569"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3530085"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3585105"},{"key":"ref28","article-title":"SM3Det: A unified model for multi-modal remote sensing object detection","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216198"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3206062"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3270801"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3545681"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3563591"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3560315"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3584963"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3579272"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3566228"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3588415"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3572486"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3587287"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3509725"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3367934"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3169339"},{"key":"ref46","article-title":"YOLOv3: An incremental improvement","author":"Redmon"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4227745"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3418965"},{"key":"ref51","first-page":"6364","article-title":"Rethinking multi-modal object detection from the perspective of mono-modality feature learning","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhang","year":"2025"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/11278119\/11270224.pdf?arnumber=11270224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T05:55:36Z","timestamp":1766728536000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/jstars.2025.3637891","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}