{"id":"https://openalex.org/W4416052645","doi":"https://doi.org/10.1109/iccv51701.2025.00693","title":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","display_name":"TerraMind: Large-Scale Generative Multimodality for Earth Observation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416052645","doi":"https://doi.org/10.1109/iccv51701.2025.00693"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.11171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014669175","display_name":"Johannes Jakubik","orcid":"https://orcid.org/0000-0002-6235-0300"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Johannes Jakubik","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Felix Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Yang","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042112718","display_name":"Benedikt Blumenstiel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedikt Blumenstiel","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093213992","display_name":"Erik Scheurer","orcid":"https://orcid.org/0009-0000-9396-2994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Scheurer","raw_affiliation_strings":["Forschungszentrum Jülich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Forschungszentrum Jülich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082191714","display_name":"Rocco Sedona","orcid":"https://orcid.org/0000-0003-4089-972X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rocco Sedona","raw_affiliation_strings":["Forschungszentrum Jülich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Forschungszentrum Jülich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116640985","display_name":"Stefano Maurogiovanni","orcid":"https://orcid.org/0009-0002-3126-4044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefano Maurogiovanni","raw_affiliation_strings":["Forschungszentrum Jülich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Forschungszentrum Jülich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104337968","display_name":"Jente Bosmans","orcid":null},"institutions":[{"id":"https://openalex.org/I2801994115","display_name":"European Space Agency","ror":"https://ror.org/03wd9za21","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2801994115"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jente Bosmans","raw_affiliation_strings":["European Space Agency Φ-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Space Agency Φ-Lab","institution_ids":["https://openalex.org/I2801994115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052528008","display_name":"Nikolaos Dionelis","orcid":"https://orcid.org/0000-0001-9662-8537"},"institutions":[{"id":"https://openalex.org/I2801994115","display_name":"European Space Agency","ror":"https://ror.org/03wd9za21","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2801994115"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nikolaos Dionelis","raw_affiliation_strings":["European Space Agency Φ-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Space Agency Φ-Lab","institution_ids":["https://openalex.org/I2801994115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089472869","display_name":"Valerio Marsocci","orcid":"https://orcid.org/0000-0003-1442-7155"},"institutions":[{"id":"https://openalex.org/I2801994115","display_name":"European Space Agency","ror":"https://ror.org/03wd9za21","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2801994115"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Valerio Marsocci","raw_affiliation_strings":["European Space Agency Φ-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Space Agency Φ-Lab","institution_ids":["https://openalex.org/I2801994115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120319205","display_name":"Niklas Kopp","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niklas Kopp","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010966122","display_name":"Rahul Ramachandran","orcid":"https://orcid.org/0000-0002-0647-1941"},"institutions":[{"id":"https://openalex.org/I4210161256","display_name":"Impact","ror":"https://ror.org/05d9dsr70","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210161256"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rahul Ramachandran","raw_affiliation_strings":["NASA IMPACT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NASA IMPACT","institution_ids":["https://openalex.org/I4210161256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062702059","display_name":"Paolo Fraccaro","orcid":"https://orcid.org/0000-0002-5213-7071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paolo Fraccaro","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034679430","display_name":"Thomas Brunschwiler","orcid":"https://orcid.org/0000-0002-7254-3405"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Brunschwiler","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058680339","display_name":"Gabriele Cavallaro","orcid":"https://orcid.org/0000-0002-3239-9904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriele Cavallaro","raw_affiliation_strings":["Forschungszentrum Jülich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Forschungszentrum Jülich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084926449","display_name":"Juan Bernab\u00e9-Moreno","orcid":"https://orcid.org/0000-0002-7786-2683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Bernabe-Moreno","raw_affiliation_strings":["IBM Research - Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Europe","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009020295","display_name":"Nicolas Long\u00e9p\u00e9","orcid":"https://orcid.org/0000-0002-6832-3274"},"institutions":[{"id":"https://openalex.org/I2801994115","display_name":"European Space Agency","ror":"https://ror.org/03wd9za21","country_code":"FR","type":"funder","lineage":["https://openalex.org/I2801994115"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Long\u00e9p\u00e9","raw_affiliation_strings":["European Space Agency Φ-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Space Agency Φ-Lab","institution_ids":["https://openalex.org/I2801994115"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5014669175"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1303,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8978206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7383","last_page":"7394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.24789999425411224,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.24789999425411224,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.2092999964952469,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.07090000063180923,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5861999988555908},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5644999742507935},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.5430999994277954},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.48890000581741333},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.47920000553131104},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4406000077724457},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42649999260902405},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4235999882221222},{"id":"https://openalex.org/keywords/earth-observation","display_name":"Earth observation","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214000225067139},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5861999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C39399123","wikidata":"https://www.wikidata.org/wiki/Q1348989","display_name":"Earth observation","level":3,"score":0.4156999886035919},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3499000072479248},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.11171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.11171","pdf_url":"https://arxiv.org/pdf/2504.11171","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.11171","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.11171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.11171","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.11171","pdf_url":"https://arxiv.org/pdf/2504.11171","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1192078525","display_name":null,"funder_award_id":"4000143501/23/I-DT","funder_id":"https://openalex.org/F4320318240","funder_display_name":"European Space Agency"}],"funders":[{"id":"https://openalex.org/F4320318240","display_name":"European Space Agency","ror":"https://ror.org/03wd9za21"},{"id":"https://openalex.org/F4320331625","display_name":"Gauss Centre for Supercomputing","ror":"https://ror.org/0585fsj26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416052645.pdf","grobid_xml":"https://content.openalex.org/works/W4416052645.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,59],"present":[1],"TerraMind,":[2],"the":[3,100,113,134],"first":[4],"any-to-any":[5],"generative,":[6],"multimodal":[7,16],"foundation":[8],"model":[9,114,135],"for":[10,91,127],"Earth":[11,92],"observation":[12],"(EO).":[13],"Unlike":[14],"other":[15],"models,":[17],"TerraMind":[18,36,50,61,95,119],"is":[19],"pretrained":[20,60],"on":[21,46,62],"dual-scale":[22,79],"representations":[23,53],"combining":[24],"both":[25],"token-level":[26],"and":[27,88,109,117,137],"pixel-level":[28],"data":[29,106],"across":[30],"modalities.":[31],"On":[32],"a":[33,47,67,84,143],"token":[34],"level,":[35,49],"encodes":[37],"high-level":[38],"contextual":[39],"information":[40],"to":[41,54,111],"learn":[42],"cross-modal":[43],"relationships,":[44],"while":[45],"pixel":[48],"leverages":[51],"fine-grained":[52],"capture":[55],"critical":[56],"spatial":[57],"nuances.":[58],"nine":[63],"geospatial":[64],"modalities":[65],"of":[66,86,102],"global,":[68],"large-scale":[69],"dataset.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"demonstrate":[75],"that":[76],"(i)":[77],"TerraMind's":[78],"early":[80],"fusion":[81],"approach":[82],"unlocks":[83],"range":[85],"zero-shot":[87],"few-shot":[89],"applications":[90],"observation,":[93],"(ii)":[94],"introduces":[96],"\"Thinking-in-Modalities\"":[97],"(TiM)":[98],"--":[99,116],"capability":[101],"generating":[103],"additional":[104],"artificial":[105],"during":[107],"finetuning":[108],"inference":[110],"improve":[112],"output":[115],"(iii)":[118],"achieves":[120],"beyond":[121],"state-of-the-art":[122],"performance":[123],"in":[124],"community-standard":[125],"benchmarks":[126],"EO":[128],"like":[129],"PANGAEA.":[130],"The":[131],"pretraining":[132],"dataset,":[133],"weights,":[136],"our":[138],"code":[139],"are":[140],"open-sourced":[141],"under":[142],"permissive":[144],"license.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}