{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:41:40Z","timestamp":1778082100709,"version":"3.51.4"},"reference-count":84,"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"}],"funder":[{"DOI":"10.13039\/100000104","name":"NASA","doi-asserted-by":"publisher","award":["80NSSC22K1487"],"award-info":[{"award-number":["80NSSC22K1487"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2329927"],"award-info":[{"award-number":["2329927"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00580","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6143-6154","source":"Crossref","is-referenced-by-count":2,"title":["WildSAT: Learning Satellite Image Representations from Wildlife Observations"],"prefix":"10.1109","author":[{"given":"Rangel","family":"Daroya","sequence":"first","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elijah","family":"Cole","sequence":"additional","affiliation":[{"name":"GenBio AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oisin Mac","family":"Aodha","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grant","family":"Van Horn","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhransu","family":"Maji","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"eBird","year":"2025"},{"key":"ref2","volume-title":"iNaturalist","year":"2025"},{"key":"ref3","article-title":"Radiant Earth Foundation, Western Cape Department of Agriculture","volume-title":"German Aerospace Center (DLR): A fusion dataset for crop type classification in Western Cape, South Africa","year":"2025"},{"key":"ref4","volume-title":"Wikipedia","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.259"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00033"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2018.09.002"},{"key":"ref12","first-page":"6320","article-title":"Spatial implicit neural representations for global-scale species mapping","volume-title":"International Conference on Machine Learning","author":"Cole","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10642394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-X-2-2024-41-2024"},{"key":"ref17","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref18","article-title":"ESA","year":"2022","journal-title":"Sentinel-1-missions-sentinel online-sentinel online. Eur. Sp. Agency"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21444"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/joc.5086"},{"key":"ref21","article-title":"Training batchnorm and only batchnorm: On the expressive power of random features in cnns","volume-title":"International Conference on Learning Representations","author":"Frankle","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs10101604"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2008.80"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0563"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_10"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/rs8030166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641235"},{"key":"ref32","volume-title":"Foundation models for generalist geospatial artificial intelligence","author":"Jakubik","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.rsase.2023.101093"},{"key":"ref34","article-title":"Learning tri-modal embeddings for zero-shot soundscape mapping","author":"Khanal","year":"2023","journal-title":"BMVC"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32457"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/rs11030293"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2681128"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2223"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-023-02206-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref43","first-page":"1940","article-title":"Overview of geolifeclef 2022: Predicting species presence from multi-modal remote sensing, bioclimatic and pedologic data","author":"Lorieul","year":"2022","journal-title":"CLEF (Working Notes)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00969"},{"key":"ref45","first-page":"23498","article-title":"Csp: Self-supervised contrastive spatial pre-training for geospatial-visual representations","volume-title":"International Conference on Machine Learning","author":"Mai"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00509"},{"key":"ref47","article-title":"Remote sensing vision-language foundation models without annotations via ground remote alignment","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mall","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.626"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111968"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14358\/PERS.83.10.737"},{"key":"ref52","article-title":"Generative representational instruction tuning","volume-title":"ICLR 2024 Workshop: How Far Are We From AGI","author":"Muennighoff","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_10"},{"key":"ref54","article-title":"In-domain representation learning for remote sensing","author":"Neumann","year":"2019","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2726"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30235"},{"key":"ref58","article-title":"Geoplant: Spatial plant species prediction dataset","author":"Picek","year":"2024","journal-title":"Advances in Neural Information Processing Systems - Datasets and Benchmark"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref60","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet","volume-title":"International conference on machine learning","author":"Recht","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00698"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00179"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.biocon.2009.05.006"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900532"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11069-020-04124-3"},{"key":"ref67","article-title":"Satbird: a dataset for bird species distribution modeling using remote sensing and citizen science data","volume":"36","author":"Teng","year":"2023","journal-title":"Advances in Neural Information Processing Systems - Datasets and Benchmarks"},{"issue":"16","key":"ref68","article-title":"Canopy height mapping by sentinel 1 and 2 satellite images","volume":"14","author":"de Almeida","year":"2022","journal-title":"airborne lidar data, and machine learning. Remote Sensing"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/502"},{"key":"ref70","first-page":"GC45I","article-title":"Esa worldcover: Global land cover mapping at 10 m resolution for 2020 based on sentinel-1 and 2 data","volume-title":"AGU Fall Meeting Abstracts","author":"Van","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref72","article-title":"Geoclip: Clip-inspired alignment between locations and images for effective worldwide geolocalization","author":"Vivanco Cepeda","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2007.895830"},{"key":"ref74","first-page":"28","article-title":"isaid: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Waqas Zamir","year":"2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/rs70403907"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113695"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2020.111716"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00214"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3475824"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2017.2762307"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2020.2964708"}],"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\/11446208.pdf?arnumber=11446208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:34:02Z","timestamp":1777530842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00580","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}