{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T10:29:07Z","timestamp":1784284147892,"version":"3.55.0"},"reference-count":193,"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\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225113"],"award-info":[{"award-number":["62225113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovative Research Group Project of Hubei Province","award":["2024AFA017"],"award-info":[{"award-number":["2024AFA017"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFB3903405"],"award-info":[{"award-number":["2022YFB3903405"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFC2705700"],"award-info":[{"award-number":["2023YFC2705700"]}]}],"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.2024.3408154","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T20:49:27Z","timestamp":1717534167000},"page":"11632-11654","source":"Crossref","is-referenced-by-count":128,"title":["MTP: Advancing Remote Sensing Foundation Model via Multitask Pretraining"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6360-4360","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, iFlytek Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, iFlytek Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, iFlytek Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erzhong","family":"Gao","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, iFlytek Company Ltd., Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0209-5309","authenticated-orcid":false,"given":"Chengxi","family":"Han","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3778-2793","authenticated-orcid":false,"given":"Haonan","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Institute of Artificial Intelligence, National Engineering Research Center for Multimedia Software, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6890-3650","authenticated-orcid":false,"given":"Liangpei","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.04.020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111716"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2196404"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3007029"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"Aerial scene parsing: From tile-level scene classification to pixel-wise semantic labeling","author":"Long","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs14225675"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3271312"},{"key":"ref13","first-page":"8815","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref21","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00803"},{"key":"ref25","first-page":"23498","article-title":"CSP: Self-supervised contrastive spatial pre-training for geospatial-visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mai","year":"2023"},{"key":"ref26","first-page":"8690","article-title":"GeoCLIP: Clip-inspired alignment between locations and images for effective worldwide geo-localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cepeda","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref31","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cong","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3316166"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3362475"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref37","article-title":"CtxMIM: Context-enhanced masked image modeling for remote sensing image understanding","author":"Zhang","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268232"},{"key":"ref39","first-page":"20054","article-title":"Cross-scale MAE: A tale of multiscale exploitation in remote sensing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2023"},{"key":"ref40","first-page":"5506","article-title":"CROMA: Remote sensing representations with contrastive radar-optical masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fuller","year":"2023"},{"key":"ref41","article-title":"Feature guided masked autoencoder for self-supervised learning in remote sensing","author":"Wang","year":"2023"},{"key":"ref42","article-title":"SkySense: A multi-modal remote sensing foundation model towards universal interpretation for Earth observation imagery","author":"Guo","year":"2023"},{"key":"ref43","article-title":"DeCUR: Decoupling common & unique representations for multimodal self-supervision","author":"Wang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10282433"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3354031"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111322"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115569"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/514434c"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3202499"},{"key":"ref53","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref61","article-title":"Should we be pre-training? An argument for end-task aware training as an alternative","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dery","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3090418"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3354783"},{"key":"ref66","article-title":"Florence: A new foundation model for computer","author":"Yuan","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref68","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref70","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref72","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3347693"},{"key":"ref74","article-title":"RSGPT: A remote sensing vision language model and benchmark","author":"Hu","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237896"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref81","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","volume-title":"Proc. NeurIPS Track Datasets Benchmarks","author":"Wang","year":"2021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref85","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref88","article-title":"Layer normalization","author":"Lei Ba","year":"2016"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref90","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref93","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref96","article-title":"In-domain representation learning for remote sensing","author":"Neumann","year":"2019"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3371481"},{"key":"ref99","article-title":"USat: A unified self-supervised encoder for multi-sensor satellite imagery","author":"Irvin","year":"2023"},{"key":"ref100","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02627","article-title":"Rethinking transformers pre-training for multi-spectral satellite imagery","author":"Noman","year":"2024"},{"key":"ref101","article-title":"xView: Objects in context in overhead imagery","author":"Lam","year":"2018"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3108476"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3064599"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183022"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00832"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974745"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19975"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222906"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00281"},{"key":"ref118","first-page":"18381","article-title":"Learning high-precision bounding box for rotated object detection via Kullback-Leibler divergence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2021"},{"key":"ref119","first-page":"11830","article-title":"Rethinking rotated object detection with Gaussian Wasserstein distance loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2021"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3136350"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3149780"},{"key":"ref122","article-title":"PP-YOLOE-R: An efficient anchor-free rotated object detector","author":"Wang","year":"2022"},{"key":"ref123","article-title":"PP-YOLOE: An evolved version of YOLO","author":"Xu","year":"2022"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00187"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148874"},{"key":"ref126","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3327123"},{"key":"ref128","article-title":"The KFIoU loss for rotated object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2023"},{"key":"ref129","article-title":"RTMDet: An empirical study of designing real-time object detectors","author":"Lyu","year":"2022"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00707"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3348479"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00606"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28502"},{"key":"ref136","article-title":"HiViT: A simpler and more efficient design of hierarchical vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref137","article-title":"SpaceNet: A remote sensing dataset and challenge series","author":"Etten","year":"2018"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3097148"},{"key":"ref143","article-title":"High-resolution representations for labeling pixels and regions","author":"Sun","year":"2019"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3238648"},{"key":"ref147","article-title":"Hi-ResNet: A high-resolution remote sensing network for semantic segmentation","author":"Chen","year":"2023"},{"key":"ref148","article-title":"AerialFormer: Multi-resolution transformer for aerial image segmentation","author":"Yamazaki","year":"2023"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3056416"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095166"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3091758"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.03.005"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3264802"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3271024"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"ref157","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2021"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3300533"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089332"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3085870"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3381752"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3236664"},{"key":"ref163","article-title":"DDPM-CD: Remote sensing change detection using denoising diffusion probabilistic models","author":"Bandara","year":"2022"},{"key":"ref164","article-title":"DeepCL: Deep change feature learning on remote sensing images in the metric space","author":"Guo","year":"2023"},{"key":"ref165","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3362895"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01491"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3349868"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2023.2225228"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3169479"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3227098"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108960"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1145\/3437802.3437810"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01994"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10283341"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183707"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3310208"},{"key":"ref180","article-title":"Time travelling pixels: Bitemporal features integration with foundation model for remote sensing image change detection","author":"Chen","year":"2023"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3277496"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3296383"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3370568"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3275140"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3327780"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3226418"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.004"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3365825"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8518015"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2858817"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLII-2-565-2018"}],"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\/10547536.pdf?arnumber=10547536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T03:29:05Z","timestamp":1732159745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10547536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":193,"URL":"https:\/\/doi.org\/10.1109\/jstars.2024.3408154","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}