{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T02:04:21Z","timestamp":1778897061892,"version":"3.51.4"},"reference-count":76,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00693","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7383-7394","source":"Crossref","is-referenced-by-count":7,"title":["TerraMind: Large-Scale Generative Multimodality for Earth Observation"],"prefix":"10.1109","author":[{"given":"Johannes","family":"Jakubik","sequence":"first","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Felix","family":"Yang","sequence":"additional","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Benedikt","family":"Blumenstiel","sequence":"additional","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Erik","family":"Scheurer","sequence":"additional","affiliation":[{"name":"Forschungszentrum Jülich"}]},{"given":"Rocco","family":"Sedona","sequence":"additional","affiliation":[{"name":"Forschungszentrum Jülich"}]},{"given":"Stefano","family":"Maurogiovanni","sequence":"additional","affiliation":[{"name":"Forschungszentrum Jülich"}]},{"given":"Jente","family":"Bosmans","sequence":"additional","affiliation":[{"name":"European Space Agency Φ-Lab"}]},{"given":"Nikolaos","family":"Dionelis","sequence":"additional","affiliation":[{"name":"European Space Agency Φ-Lab"}]},{"given":"Valerio","family":"Marsocci","sequence":"additional","affiliation":[{"name":"European Space Agency Φ-Lab"}]},{"given":"Niklas","family":"Kopp","sequence":"additional","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Rahul","family":"Ramachandran","sequence":"additional","affiliation":[{"name":"NASA IMPACT"}]},{"given":"Paolo","family":"Fraccaro","sequence":"additional","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Thomas","family":"Brunschwiler","sequence":"additional","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Gabriele","family":"Cavallaro","sequence":"additional","affiliation":[{"name":"Forschungszentrum Jülich"}]},{"given":"Juan","family":"Bernabe-Moreno","sequence":"additional","affiliation":[{"name":"IBM Research - Europe"}]},{"given":"Nicolas","family":"Long\u00e9p\u00e9","sequence":"additional","affiliation":[{"name":"European Space Agency Φ-Lab"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref2","article-title":"Copernicus dem","year":"2022"},{"key":"ref3","article-title":"Anysat: An earth observation model for any resolutions, scales, and modalities","volume-title":"arXiv preprint arXiv:2412.14123","author":"Astruc","year":"2024"},{"key":"ref4","article-title":"Omnisat: Self-supervised modality fusion for earth observation","author":"Astruc","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.199"},{"key":"ref6","article-title":"SSL4EOS12 v1.1 - A Multimodal, Multiseasonal Dataset for Pretraining","volume-title":"arXiv preprint arXiv:2503.00168","author":"Blumenstiel","year":"2025"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW67362.2025.00225","article-title":"Terramesh: A planetary mosaic of multimodal earth observation data","volume-title":"arXiv preprint arXiv:2504.11172","author":"Blumenstiel","year":"2025"},{"key":"ref8","article-title":"On the opportunities and risks of foundation models","volume-title":"arXiv preprint arXiv:2108.07258","author":"Bommasani","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00113"},{"key":"ref10","article-title":"An introduction to vision-language modeling","volume-title":"arXiv preprint arXiv:2405.17247","author":"Bordes","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_34"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02061"},{"key":"ref13","article-title":"Self-supervised change detection in multi-view remote sensing images","volume-title":"arXiv preprint arXiv:2103.05969","author":"Chen","year":"2021"},{"key":"ref14","article-title":"SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network","volume":"15","author":"Wang","year":"2022","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS)"},{"key":"ref15","article-title":"Sample4geo: Hard negative sampling for cross-view geolocalisation","volume-title":"arXiv preprint arXiv:2303.11851","author":"Deuser","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.01.014"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref18","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref19","article-title":"xview2 1st place solution","author":"Durnov"},{"key":"ref20","article-title":"Spacenet: A remote sensing dataset and challenge series","author":"Van Etten","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10642780"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3391625"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/IGARSS53475.2024.10640760","article-title":"Major tom: Expandable datasets for earth observation","volume-title":"arXiv preprint arXiv:2402.12095","author":"Francis","year":"2024"},{"key":"ref24","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","volume-title":"arXiv preprint arXiv:2405.21075","author":"Fu","year":"2024"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.52202\/075280-0241","article-title":"Croma: Remote sensing representations with contrastive radar-optical masked autoencoders","author":"Fuller","year":"2023"},{"key":"ref26","article-title":"FLAIR : a country-scale land cover semantic segmentation dataset from multi-source optical imagery","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Garioud","year":"2023"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1109\/MGRS.2025.3546527","article-title":"Lossy neural compression for geospatial analytics: A review","volume-title":"arXiv preprint arXiv:2503.01505","author":"Gomes","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2022.113192"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02631","article-title":"Bridging remote sensors with multisensor geospatial foundation models","author":"Han","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3689177"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref32","article-title":"Foundation models for generalist geospatial artificial intelligence","author":"Jakubik","year":"2023"},{"key":"ref33","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","author":"Toutanova","year":"2019"},{"key":"ref34","article-title":"Diffusionsat: A generative foundation model for satellite imagery","author":"Khanna","year":"2023"},{"issue":"7","key":"ref35","article-title":"Method for Image Quality Evaluation of Satellite-based SAR Data","volume":"14","author":"Arai","year":"2023","journal-title":"International Journal of Advanced Computer Science and Applications (IJACSA)"},{"key":"ref36","article-title":"Is self-supervised pre-training on satellite imagery better than imagenet? a systematic study with sentinel- 2","volume-title":"arXiv preprint arXiv:2502.10669","author":"Lahrichi","year":"2025"},{"key":"ref37","article-title":"Llavanext: Stronger llms supercharge multimodal capabilities in the wild","author":"Li","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102926"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/MGRS.2024.3383473","article-title":"Vision-language models in remote sensing: Current progress and future trends","author":"Li","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3390838","article-title":"Remoteclip: A vision language foundation model for remote sensing","author":"Liu","year":"2024"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01167","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3033424"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3557915.3561043"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref47","article-title":"Beyond the visible: Multispectral vision-language learning for earth observation","volume-title":"arXiv preprint arXiv:2503.15969","author":"Marimo","year":"2025"},{"key":"ref48","article-title":"Cross-sensor selfsupervised training and alignment for remote sensing","author":"Marsocci","year":"2024"},{"key":"ref49","article-title":"Pangaea: A global and inclusive benchmark for geospatial foundation models","volume-title":"arXiv preprint arXiv:2412.04204","author":"Marsocci","year":"2024"},{"key":"ref50","article-title":"Gfm: Building geospatial foundation models via continual pretraining","volume-title":"arXiv preprint arXiv:2302.04476","author":"Mendieta","year":"2023"},{"key":"ref51","article-title":"Finite scalar quantization: Vq-vae made simple","volume-title":"arXiv preprint arXiv:2309.15505","author":"Mentzer","year":"2023.4,15"},{"key":"ref52","article-title":"4m: Massively multimodal masked modeling","author":"Mizrahi","year":"2023"},{"key":"ref53","article-title":"Biomassters: A benchmark dataset for forest biomass estimation using multi-modal satellite time-series","volume-title":"Thirtyseventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Nascetti","year":"2023"},{"key":"ref54","article-title":"Mmearth: Exploring multi-modal pretext tasks for geospatial representation learning","volume-title":"arXiv preprint arXiv:2405.02771","author":"Nedungadi","year":"2024"},{"key":"ref55","article-title":"xview3-sar: Detecting dark fishing activity using synthetic aperture radar imagery","author":"Paolo","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icaccaf.2016.7748978"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/rs14040871"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref61","article-title":"Representation learning for remote sensing: An unsupervised sensor fusion approach","volume-title":"arXiv preprint arXiv:2108.05094","author":"Swope","year":"2021"},{"key":"ref62","article-title":"Artificial intelligence to advance earth observation: a perspective","author":"Tuia","year":"2023"},{"key":"ref63","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref64","doi-asserted-by":"crossref","DOI":"10.1109\/MGRS.2022.3198244","article-title":"Self-supervised learning in remote sensing: A review","volume-title":"arXiv preprint arXiv:2206.13188","author":"Wang","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2023.3281651"},{"key":"ref66","first-page":"69925","article-title":"Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref67","article-title":"Accelerating Diffusion for SAR-to-Optical Image Translation via Adversarial Consistency Distillation","author":"Bai","year":"2024"},{"key":"ref68","article-title":"Neural plasticity-inspired foundation model for observing the earth crossing modalities","author":"Xiong","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref70","article-title":"Multi-modal graph neural networks for localized off-grid weather forecasting","volume-title":"arXiv preprint arXiv:2410.12938","author":"Yang","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3507010"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114417"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3219816"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2017.2762307"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445875.pdf?arnumber=11445875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:25Z","timestamp":1777611805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445875\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00693","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}