{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:29:55Z","timestamp":1773772195737,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["61675036"],"award-info":[{"award-number":["61675036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Equipment Pre-Research Fund","doi-asserted-by":"publisher","award":["6140415020312"],"award-info":[{"award-number":["6140415020312"]}],"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":[[2025]]},"DOI":"10.1109\/tgrs.2025.3587389","type":"journal-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:18:30Z","timestamp":1752103110000},"page":"1-23","source":"Crossref","is-referenced-by-count":3,"title":["Prototype-Guided Multilayer Alignment Network for Few-Shot Object Detection in Remote Sensing"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9336-2774","authenticated-orcid":false,"given":"Abdullah","family":"Azeem","sequence":"first","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5275-1728","authenticated-orcid":false,"given":"Zhengzhou","family":"Li","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4131-9665","authenticated-orcid":false,"given":"Abubakar","family":"Siddique","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4940-1396","authenticated-orcid":false,"given":"Yuting","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5955-2999","authenticated-orcid":false,"given":"Yongsong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3246565"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3437460"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.03.014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.06.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00534"},{"key":"ref8","article-title":"Frustratingly simple few-shot object detection","author":"Wang","year":"2020","journal-title":"arXiv:2003.06957"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3051383"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3091003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078507"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3066539"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs14122790"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3546062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3347329"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367666"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3367168"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2024.3505602"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102508"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250448"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs15051187"},{"key":"ref23","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. NeurIPS","author":"Nagrani"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26263"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.12.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3400595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25129"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"ref30","first-page":"28","article-title":"ISAID: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Zamir"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3502421"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref39","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref40","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","volume-title":"Proc. ICLR Poster","author":"Zhang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref42","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. ICLR Poster","author":"Liu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3456240"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3364713"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3300154"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369666"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/rs15225372"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.004"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359316"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88480-2_63"},{"key":"ref52","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"arXiv:2205.14100"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3386311"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref57","article-title":"PaLI: A jointly-scaled multilingual language-image model","author":"Chen","year":"2022","journal-title":"arXiv:2209.06794"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00057"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.811"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref61","article-title":"Multi-stage knowledge integration of vision-language models for continual learning","author":"Zhang","year":"2024","journal-title":"arXiv: 2411.06764"},{"key":"ref62","article-title":"Learning without forgetting for vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv:2305.19270"},{"key":"ref63","article-title":"One VLM to keep it learning: Generation and balancing for data-free continual visual question answering","author":"Das","year":"2024","journal-title":"arXiv:2411.02210"},{"key":"ref64","article-title":"Advancing cross-domain discriminability in continual learning of vision-language models","author":"Xu","year":"2024","journal-title":"arXiv:2406.18868"},{"key":"ref65","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2104.10858"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01781"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129718"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref72","article-title":"ITA: Image-text alignments for multi-modal named entity recognition","author":"Wang","year":"2021","journal-title":"arXiv:2112.06482"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859720"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00086"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3528262"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00202"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11075727.pdf?arnumber=11075727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T18:08:40Z","timestamp":1753121320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11075727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3587389","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}