{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:08:37Z","timestamp":1783613317332,"version":"3.55.0"},"reference-count":47,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Ministry of Education Humanities and Social Science Research Planning Fund Project","award":["23YJAZH079"],"award-info":[{"award-number":["23YJAZH079"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jstars.2024.3447086","type":"journal-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T23:30:00Z","timestamp":1724283000000},"page":"14823-14835","source":"Crossref","is-referenced-by-count":11,"title":["PERS: Parameter-Efficient Multimodal Transfer Learning for Remote Sensing Visual Question Answering"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8891-554X","authenticated-orcid":false,"given":"Jinlong","family":"He","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7032-8429","authenticated-orcid":false,"given":"Gang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4234-1579","authenticated-orcid":false,"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaonan","family":"Su","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhua","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongze","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6542-649X","authenticated-orcid":false,"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/rs13214342"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2019.2899129"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3026587"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044958"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2975541"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988032"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994150"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988294"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3035561"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9553624"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3237606"},{"key":"ref20","first-page":"1","article-title":"How to find a good image-text embedding for remote sensing visual question answering?","volume-title":"Proc. MACLEAN: Mach. Learn. Earth Observ. Workshop Co-Located Eur. Conf. Mach. Learn. Princ. Pract. Knowl. Discov. Databases","volume":"3088","author":"Chappuis","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00122"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.196"},{"key":"ref26","first-page":"20989","article-title":"Sparse and continuous attention mechanisms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 33: Annu. Conf. Neural Inf. Process. Syst.","author":"Martins","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3192460"},{"key":"ref29","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref30","first-page":"1","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst.","author":"Pan","year":"2022"},{"key":"ref31","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst.","author":"Rebuffi","year":"2017"},{"key":"ref32","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Houlsby","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01435"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref36","first-page":"1","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref37","first-page":"1","article-title":"Advancing plain vision transformer towards remote sensing foundation model","volume":"61","author":"Wang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref38","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proc. 54th Annu. Meeting Association Comput. Linguistics (Volume 1: Long Papers)","author":"Sennrich","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/igarss47720.2021.9553307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref42","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2024.3389042"},{"key":"ref44","article-title":"Multi-modal fusion transformer for visual question answering in remote sensing","author":"Siebert","year":"2022","journal-title":"Remote Sens."},{"key":"ref45","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/igarss52108.2023.10281674"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/10330207\/10643278.pdf?arnumber=10643278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:20:30Z","timestamp":1725686430000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/jstars.2024.3447086","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}