{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:42Z","timestamp":1778048502163,"version":"3.51.4"},"reference-count":106,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00029","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"212-224","source":"Crossref","is-referenced-by-count":0,"title":["MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data"],"prefix":"10.1109","author":[{"given":"Antoine","family":"Labatie","sequence":"first","affiliation":[{"name":"Institut National de 1’Information géographique et forestière (IGN),France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Vaccaro","sequence":"additional","affiliation":[{"name":"Institut National de 1’Information géographique et forestière (IGN),France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nina","family":"Lardiere","sequence":"additional","affiliation":[{"name":"Institut National de 1’Information géographique et forestière (IGN),France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anatol","family":"Garioud","sequence":"additional","affiliation":[{"name":"Institut National de 1’Information géographique et forestière (IGN),France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Gonthier","sequence":"additional","affiliation":[{"name":"Institut National de 1’Information géographique et forestière (IGN),France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5194\/essd-15-681-2023"},{"issue":"5","key":"ref2","first-page":"51","article-title":"Major limitations of satellite images","volume":"4","author":"Al-Wassai","year":"2013","journal-title":"Journal of Global Research in Computer Science"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_24"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01819"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3643453"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00223"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0015"},{"key":"ref14","article-title":"TerraFM: A scalable foundation model for unified multisensor earth observation","author":"Danish","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00580"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3602237"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3678717.3691292"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref20","article-title":"SatMamba: Development of foundation models for remote sensing imagery using state space models","author":"Duc","year":"2025"},{"key":"ref21","first-page":"1","article-title":"Self-supervised spatio-temporal representation learning of satel lite image time series","author":"Dumeur","year":"2024","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"ref22","first-page":"12371","article-title":"Scalable pre-training of large autoregressive image models","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"El-Nouby"},{"key":"ref23","volume-title":"S2-NAIP","author":"Face","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00138"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365287.1095"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30160-0_4910"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0724"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2026.04.017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65742-0_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00483"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.03.012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02631"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00921"},{"key":"ref38","article-title":"USat: A unified self-supervised encoder for multi-sensor satellite imagery","author":"Irvin","year":"2023"},{"key":"ref39","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Conference on Uncertainty in Artificial Intelligence (UAI)","author":"Izmailov"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3204888"},{"key":"ref41","article-title":"Foundation models for generalist geospatial artificial intelligence","author":"Jakubik","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00693"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00284"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02146"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4219"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.09.013"},{"key":"ref47","article-title":"SeaMo: A multi-seasonal and multi-modal remote sensing foundation model","author":"Li","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2026.3656362"},{"key":"ref49","first-page":"260","article-title":"Masked angle-aware autoencoder for remote sensing images","volume-title":"European Conference on Computer Vision","author":"Li"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3331717"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00605"},{"key":"ref52","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.09.004"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0559"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref58","article-title":"Exponential moving average of weights in deep learning: Dynamics and benefits","author":"Morales-Brotons","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268232"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_10"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02627"},{"key":"ref62","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00207"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85187-2_20"},{"key":"ref65","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref67","article-title":"Position: mission critical - satellite data is a distinct modality in machine learning","author":"Rolf","year":"2024"},{"key":"ref68","article-title":"Scaling law for language models training considering batch size","author":"Shuai","year":"2024"},{"key":"ref69","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025"},{"key":"ref70","article-title":"EarthPT: a time series foundation model for earth observation","volume-title":"NeurIPS CCAI workshop","author":"Smith"},{"key":"ref71","article-title":"SatVision-TOA: A geospatial foundation model for coarse-resolution all-sky remote sensing imagery","author":"Spradlin","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00091"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3642610"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0879"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01004"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3371481"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113888"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref80","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref81","article-title":"Lightweight, pre-trained transformers for remote sensing timeseries","author":"Tseng","year":"2023"},{"key":"ref82","article-title":"Galileo: Learning global & local features of many remote sensing modalities","volume-title":"Forty-second International Conference on Machine Learning","author":"Tseng"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00136"},{"key":"ref85","article-title":"Automatic data curation for self-supervised learning: A clustering-based approach","author":"Vo","year":"2024"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00207"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3557581"},{"key":"ref90","article-title":"Scaling efficient masked image modeling on large remote sensing dataset","author":"Wang","year":"2024"},{"key":"ref91","article-title":"RoMA: Scaling up mamba-based foundation models for remote sensing","author":"Wang","year":"2025"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883983"},{"key":"ref93","article-title":"RingMolite: A remote sensing multi-task lightweight network with cnn-transformer hybrid framework","author":"Wang","year":"2023"},{"key":"ref94","first-page":"286","article-title":"Decoupling common and unique representations for multi-modal self-supervised learning","volume-title":"European Conference on Computer Vision","author":"Wang"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3466896"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3493237"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00922"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00251"},{"key":"ref99","article-title":"Zooming out on zooming in: Advancing super-resolution for remote sensing","author":"Wolters","year":"2023"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01078-8"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref102","article-title":"Neural plasticity-inspired multimodal foundation model for earth observation","author":"Xiong","year":"2024"},{"key":"ref103","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"You","year":"2019"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2026.3664662"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00854"},{"key":"ref106","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"International Conference on Learning Representations","author":"Zhou"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492731.pdf?arnumber=11492731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:06Z","timestamp":1778047626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00029","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}