{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:56:45Z","timestamp":1786039005533,"version":"3.56.0"},"reference-count":66,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301093"],"award-info":[{"award-number":["62301093"]}],"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":["U2133211"],"award-info":[{"award-number":["U2133211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZC20233336"],"award-info":[{"award-number":["GZC20233336"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M730425"],"award-info":[{"award-number":["2023M730425"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023CDJXY-037"],"award-info":[{"award-number":["2023CDJXY-037"]}],"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.2024.3398038","type":"journal-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T17:34:04Z","timestamp":1715189644000},"page":"1-15","source":"Crossref","is-referenced-by-count":44,"title":["MeSAM: Multiscale Enhanced Segment Anything Model for Optical Remote Sensing Images"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3304-3045","authenticated-orcid":false,"given":"Xichuan","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1723-4651","authenticated-orcid":false,"given":"Fu","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0948-1600","authenticated-orcid":false,"given":"Lihui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianqian","family":"Song","sequence":"additional","affiliation":[{"name":"School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9542-0638","authenticated-orcid":false,"given":"Gemine","family":"Vivone","sequence":"additional","affiliation":[{"name":"National Research Council, Institute of Methodologies for Environmental Analysis, CNR-IMAA, Tito, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4817-2875","authenticated-orcid":false,"given":"Jocelyn","family":"Chanussot","sequence":"additional","affiliation":[{"name":"University Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3264232"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.01.020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093977"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095835"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111716"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3116147"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","article-title":"Anti-oversmoothing in deep vision transformers via the Fourier domain analysis: From theory to practice","author":"Wang","year":"2022","journal-title":"arXiv:2203.05962"},{"key":"ref13","article-title":"RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model","author":"Chen","year":"2023","journal-title":"arXiv:2306.16269"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103540"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref16","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref17","article-title":"SAM fails to segment anything\u2014SAM-adapter: Adapting SAM in underperformed scenes: Camouflage, shadow, medical image segmentation, and more","author":"Chen","year":"2023","journal-title":"arXiv:2304.09148"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2019.1706009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi9040256"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3052886"},{"key":"ref24","first-page":"1","article-title":"An image is worth 16\\times16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3119654"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/rs15071860"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"ref28","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"issue":"1","key":"ref29","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang"},{"key":"ref31","article-title":"SkySense: A multi-modal remote sensing foundation model towards universal interpretation for Earth observation imagery","author":"Guo","year":"2023","journal-title":"arXiv:2312.10115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3316166"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3348479"},{"key":"ref34","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Cong"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref38","article-title":"RingMo-lite: A remote sensing multi-task lightweight network with CNN-transformer hybrid framework","author":"Wang","year":"2023","journal-title":"arXiv:2309.09003"},{"key":"ref39","article-title":"RemoteCLIP: A vision language foundation model for remote sensing","author":"Liu","year":"2023","journal-title":"arXiv:2306.11029"},{"key":"ref40","article-title":"RS5M and GeoRSCLIP: A large scale vision-language dataset and a large vision-language model for remote sensing","author":"Zhang","year":"2023","journal-title":"arXiv:2306.11300"},{"key":"ref41","article-title":"GeoChat: Grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2023","journal-title":"arXiv:2311.15826"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref43","article-title":"A comprehensive survey on segment anything model for vision and beyond","author":"Zhang","year":"2023","journal-title":"arXiv:2305.08196"},{"key":"ref44","article-title":"A survey on segment anything model (SAM): Vision foundation model meets prompt engineering","author":"Zhang","year":"2023","journal-title":"arXiv:2306.06211"},{"key":"ref45","article-title":"Segment anything is not always perfect: An investigation of SAM on different real-world applications","author":"Ji","year":"2023","journal-title":"arXiv:2304.05750"},{"key":"ref46","article-title":"Zero-shot performance of the Segment Anything Model (SAM) in 2D medical imaging: A comprehensive evaluation and practical guidelines","author":"de Oliveira","year":"2023","journal-title":"arXiv:2305.00109"},{"key":"ref47","article-title":"SAM on medical images: A comprehensive study on three prompt modes","author":"Cheng","year":"2023","journal-title":"arXiv:2305.00035"},{"key":"ref48","article-title":"SAM meets robotic surgery: An empirical study in robustness perspective","author":"Wang","year":"2023","journal-title":"arXiv:2304.14674"},{"key":"ref49","first-page":"1","article-title":"SAM.MD: Zero-shot medical image segmentation capabilities of the segment anything model","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Wald"},{"key":"ref50","article-title":"Medical SAM adapter: Adapting segment anything model for medical image segmentation","author":"Wu","year":"2023","journal-title":"arXiv:2304.12620"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47401-9_16"},{"key":"ref52","article-title":"Customized segment anything model for medical image segmentation","author":"Zhang","year":"2023","journal-title":"arXiv:2304.13785"},{"key":"ref53","article-title":"Segment anything in high quality","author":"Ke","year":"2023","journal-title":"arXiv:2306.01567"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00406"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_70"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-45673-2_21"},{"key":"ref57","first-page":"23495","article-title":"Inception transformer","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Si"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"ref59","first-page":"1","article-title":"Scattering vision transformer: Spectral mixing matters","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Patro"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref61","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/rs10060964"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2961634"},{"key":"ref64","volume-title":"Sentinel-2 cloud mask catalogue","author":"Francis","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163065"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10522788.pdf?arnumber=10522788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T17:39:54Z","timestamp":1716399594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10522788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3398038","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}