{"id":"https://openalex.org/W4413147540","doi":"https://doi.org/10.1109/cvpr52734.2025.01334","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","display_name":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147540","doi":"https://doi.org/10.1109/cvpr52734.2025.01334"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043133731","display_name":"Sagar Soni","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sagar Soni","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115572812","display_name":"Akshay Dudhane","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Akshay Dudhane","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022144430","display_name":"Hiyam Debary","orcid":"https://orcid.org/0000-0003-1484-1794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiyam Debary","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066756540","display_name":"Mustansar Fiaz","orcid":"https://orcid.org/0000-0003-2289-2284"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mustansar Fiaz","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037593408","display_name":"Muhammad Akhtar Munir","orcid":"https://orcid.org/0000-0002-9642-0936"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Akhtar Munir","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071342791","display_name":"Muhammad Sohail Danish","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Sohail Danish","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025361716","display_name":"Campbell Watson","orcid":"https://orcid.org/0000-0003-3029-9069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Campbell D Watson","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023556527","display_name":"Levente J. Klein","orcid":"https://orcid.org/0000-0001-9497-1403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levente J Klein","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483979","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-2905-1755"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5043133731"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":78.9281,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.99902773,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14303","last_page":"14313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9664000272750854,"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"}},"topics":[{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9664000272750854,"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/T12031","display_name":"Speech and dialogue systems","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9480000138282776,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.6087823510169983},{"id":"https://openalex.org/keywords/earth","display_name":"Earth (classical element)","score":0.5611476302146912},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5119694471359253},{"id":"https://openalex.org/keywords/sensory-system","display_name":"Sensory system","score":0.4960666596889496},{"id":"https://openalex.org/keywords/astrobiology","display_name":"Astrobiology","score":0.41437551379203796},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17073267698287964},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1486080288887024},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08870571851730347},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.0675269365310669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087823510169983},{"id":"https://openalex.org/C26148502","wikidata":"https://www.wikidata.org/wiki/Q2488752","display_name":"Earth (classical element)","level":2,"score":0.5611476302146912},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5119694471359253},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.4960666596889496},{"id":"https://openalex.org/C87355193","wikidata":"https://www.wikidata.org/wiki/Q411","display_name":"Astrobiology","level":1,"score":0.41437551379203796},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17073267698287964},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1486080288887024},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08870571851730347},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0675269365310669}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2478024444","https://openalex.org/W2390279801","https://openalex.org/W1637585205","https://openalex.org/W3027684452","https://openalex.org/W3087128175","https://openalex.org/W3156371387","https://openalex.org/W2327420602"],"abstract_inverted_index":{"Automated":[0],"analysis":[1,140],"of":[2,88],"vast":[3],"Earth":[4,62,69],"observation":[5],"data":[6],"via":[7],"interactive":[8],"Vision-Language":[9],"Models":[10],"(VLMs)":[11],"can":[12],"unlock":[13],"new":[14],"opportunities":[15],"for":[16,61,141],"environmental":[17],"monitoring,":[18],"disaster":[19],"response,":[20],"and":[21,46,81,100,124,131,137,160,173],"resource":[22],"management.":[23],"Existing":[24],"generic":[25,159],"VLMs":[26,39],"do":[27],"not":[28],"perform":[29],"well":[30],"on":[31,150],"Remote":[32],"Sensing":[33],"data,":[34,65],"while":[35],"the":[36],"recent":[37],"Geo-spatial":[38],"remain":[40],"restricted":[41],"to":[42],"a":[43,56,85],"fixed":[44],"resolution":[45],"few":[47],"sensor":[48],"modalities.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,106],"introduce":[54,107],"EarthDial,":[55],"conversational":[57],"assistant":[58],"specifically":[59],"designed":[60],"Observation":[63],"(EO)":[64],"transforming":[66],"complex,":[67],"multi-sensory":[68],"observations":[70],"into":[71],"interactive,":[72],"natural":[73],"language":[74],"dialogues.":[75],"EarthDial":[76,134,156],"supports":[77],"multi-":[78],"spectral,":[79],"multi-temporal,":[80],"multi-resolution":[82],"imagery,":[83],"enabling":[84],"wide":[86],"range":[87],"remote":[89],"sensing":[90],"tasks,":[91],"including":[92],"classification,":[93],"detection,":[94],"captioning,":[95],"question":[96],"answering,":[97],"visual":[98,101],"reasoning,":[99],"grounding.":[102],"To":[103],"achieve":[104],"this,":[105],"an":[108],"extensive":[109,147],"instruction":[110,116],"tuning":[111],"dataset":[112],"comprising":[113],"over":[114],"11.11M":[115],"pairs":[117],"covering":[118],"RGB,":[119],"Synthetic":[120],"Aperture":[121],"Radar":[122],"(SAR),":[123],"multispectral":[125],"modalities":[126],"such":[127],"as":[128],"Near-Infrared":[129],"(NIR)":[130],"infrared.":[132],"Furthermore,":[133],"handles":[135],"bi-temporal":[136],"multi-temporal":[138],"sequence":[139],"applications":[142],"like":[143],"change":[144],"detection.":[145],"Our":[146,170],"experimental":[148],"results":[149],"44":[151],"downstream":[152],"datasets":[153],"demonstrate":[154],"that":[155],"outperforms":[157],"existing":[158],"domain-specific":[161],"models,":[162],"achieving":[163],"better":[164],"generalization":[165],"across":[166],"various":[167],"EO":[168],"tasks.":[169],"source":[171],"codes":[172],"pre-trained":[174],"models":[175],"are":[176],"at":[177],"https://github.com/hiyamdebary/EarthDial.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9}],"updated_date":"2026-05-26T13:28:51.108037","created_date":"2025-10-10T00:00:00"}
