{"id":"https://openalex.org/W4417408781","doi":"https://doi.org/10.1109/wacv61042.2026.00508","title":"GAEA: A Geolocation Aware Conversational Assistant","display_name":"GAEA: A Geolocation Aware Conversational Assistant","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417408781","doi":"https://doi.org/10.1109/wacv61042.2026.00508"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16423","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ron Campos","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Campos","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116099709","display_name":"Ashmal Vayani","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashmal Vayani","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083240018","display_name":"P. S. Kulkarni","orcid":"https://orcid.org/0000-0001-6843-4399"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parth Parag Kulkarni","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653804","display_name":"Rohit Gupta","orcid":"https://orcid.org/0000-0002-8398-680X"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Gupta","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072789083","display_name":"Aizan Zafar","orcid":"https://orcid.org/0000-0002-1932-0595"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aizan Zafar","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aritra Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aritra Dutta","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080823547","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0001-6172-5572"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03096614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5236","last_page":"5246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.779699981212616,"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":0.779699981212616,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.17030000686645508,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006200000178068876,"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/geolocation","display_name":"Geolocation","score":0.8334000110626221},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.6092000007629395},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.572700023651123},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.42160001397132874},{"id":"https://openalex.org/keywords/geotagging","display_name":"Geotagging","score":0.41780000925064087},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.3659000098705292},{"id":"https://openalex.org/keywords/location-awareness","display_name":"Location awareness","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.8334000110626221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979999780654907},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C53605480","wikidata":"https://www.wikidata.org/wiki/Q852595","display_name":"Geotagging","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C2776104089","wikidata":"https://www.wikidata.org/wiki/Q15894079","display_name":"Location awareness","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C198613851","wikidata":"https://www.wikidata.org/wiki/Q432394","display_name":"Assisted GPS","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.16423","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16423","pdf_url":"https://arxiv.org/pdf/2503.16423","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.16423","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16423","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.16423","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16423","pdf_url":"https://arxiv.org/pdf/2503.16423","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"geolocalization,":[1,95],"in":[2],"which":[3],"an":[4,14,42,119],"AI":[5],"model":[6,30,40,217],"traditionally":[7],"predicts":[8],"the":[9,25,29,36,39,45,48,54,60,81,116,122,131,200,208],"precise":[10],"GPS":[11,37],"coordinates":[12],"of":[13,44,63,118,133],"image,":[15],"is":[16],"a":[17,108,135,141,168],"challenging":[18],"task":[19],"with":[20,53,59,181],"many":[21],"downstream":[22,91],"applications.":[23],"However,":[24,80],"user":[26,123],"cannot":[27],"utilize":[28],"to":[31,51,75,176],"further":[32],"their":[33],"knowledge":[34],"beyond":[35,85],"coordinates;":[38],"lacks":[41],"understanding":[43],"location":[46,117],"and":[47,70,148,159,191,194,207,218],"conversational":[49,109,178],"ability":[50],"communicate":[52],"user.":[55],"In":[56,98],"recent":[57],"days,":[58],"tremendous":[61],"progress":[62],"large":[64],"multimodal":[65],"models":[66],"(LMMs),":[67],"both":[68],"proprietary":[69,192,210],"open-source":[71,190,202],"researchers":[72],"have":[73],"attempted":[74],"geolocalize":[76],"images":[77,147],"using":[78],"LMMs.":[79],"issues":[82],"remain":[83],"unaddressed;":[84],"general":[86],"tasks,":[87,92],"for":[88],"more":[89],"specialized":[90],"such":[93,134],"as":[94,121],"LMMs":[96,193],"struggle.":[97],"this":[99,104],"work,":[100],"we":[101,138,166],"propose":[102,139,167],"solving":[103],"problem":[105],"by":[106,154,205,213],"introducing":[107],"model,":[110,203,211],"GAEA,":[111],"that":[112,129,196],"provides":[113],"information":[114],"regarding":[115],"image":[120],"requires.":[124],"No":[125],"large-scale":[126],"dataset":[127,143],"exists":[128],"enables":[130],"training":[132],"model.":[136],"Thus,":[137],"GAEA-1.4M,":[140],"comprehensive":[142],"comprising":[144,172],"over":[145],"800k":[146],"approximately":[149],"1.4M":[150],"question-answer":[151],"pairs,":[152],"constructed":[153],"leveraging":[155],"OpenStreetMap":[156],"(OSM)":[157],"attributes":[158],"geographical":[160],"context":[161],"clues.":[162],"For":[163],"quantitative":[164],"evaluation,":[165],"diverse":[169,182],"benchmark,":[170],"GAEA-Bench,":[171],"3.5k":[173],"image-text":[174],"pairs":[175],"evaluate":[177],"capabilities":[179],"equipped":[180],"question":[183],"types.":[184],"We":[185],"consider":[186],"11":[187],"state-":[188],"of-the-art":[189],"demonstrate":[195],"GAEA":[197],"significantly":[198],"outperforms":[199],"best":[201,209],"LLaVA-OneVision,":[204],"18.2%":[206],"GPT-4o,":[212],"7.2%.":[214],"Our":[215],"dataset,":[216],"codes":[219],"are":[220],"available":[221],"https://ucf-crcv.github.io/GAEA.":[222]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
