{"id":"https://openalex.org/W4415824654","doi":"https://doi.org/10.1145/3728482.3757386","title":"VICI: VLM-Instructed Cross-view Image-localisation","display_name":"VICI: VLM-Instructed Cross-view Image-localisation","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415824654","doi":"https://doi.org/10.1145/3728482.3757386"},"language":null,"primary_location":{"id":"doi:10.1145/3728482.3757386","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728482.3757386","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3728482.3757386","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on UAVs in Multimedia: Capturing the World from a New Perspective","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3728482.3757386","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100431066","display_name":"Xiaohan Zhang","orcid":"https://orcid.org/0000-0001-6344-9604"},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohan Zhang","raw_affiliation_strings":["University of Vermont, Burlington, USA"],"raw_orcid":"https://orcid.org/0000-0001-6344-9604","affiliations":[{"raw_affiliation_string":"University of Vermont, Burlington, USA","institution_ids":["https://openalex.org/I111236770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076440529","display_name":"Tavis Shore","orcid":"https://orcid.org/0000-0002-3877-4736"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tavis Shore","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3877-4736","affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418568","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3957-7061"},"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":"Chen Chen","raw_affiliation_strings":["University of Central Florida, Orlando, USA"],"raw_orcid":"https://orcid.org/0000-0003-3957-7061","affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033644268","display_name":"Oscar M\u00e9ndez","orcid":"https://orcid.org/0000-0003-4904-4349"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oscar Mendez","raw_affiliation_strings":["Locus Robotics, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0003-4904-4349","affiliations":[{"raw_affiliation_string":"Locus Robotics, Boston, USA","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091184063","display_name":"Simon Hadfield","orcid":"https://orcid.org/0000-0001-8637-5054"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Hadfield","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-8637-5054","affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001816279","display_name":"Safwan Wshah","orcid":"https://orcid.org/0000-0001-5051-7719"},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Safwan Wshah","raw_affiliation_strings":["University of Vermont, Burlington, USA"],"raw_orcid":"https://orcid.org/0000-0001-5051-7719","affiliations":[{"raw_affiliation_string":"University of Vermont, Burlington, USA","institution_ids":["https://openalex.org/I111236770"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85432449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8948000073432922,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8948000073432922,"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":0.03539999946951866,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5823000073432922},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/satellite","display_name":"Satellite","score":0.44749999046325684},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4442000091075897},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4397999942302704},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40400001406669617},{"id":"https://openalex.org/keywords/satellite-imagery","display_name":"Satellite imagery","score":0.39500001072883606},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3874000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035999894142151},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5823000073432922},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005999803543091},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C2778102629","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite imagery","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38440001010894775},{"id":"https://openalex.org/C2985301230","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite image","level":3,"score":0.37959998846054077},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.37400001287460327},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.34040001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C2987528665","wikidata":"https://www.wikidata.org/wiki/Q854845","display_name":"Earth observation satellite","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728482.3757386","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728482.3757386","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3728482.3757386","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on UAVs in Multimedia: Capturing the World from a New Perspective","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3728482.3757386","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728482.3757386","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3728482.3757386","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on UAVs in Multimedia: Capturing the World from a New Perspective","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3481635175","display_name":"RII Track-2 FEC: Explainable and Adaptable Artificial Intelligence for Advanced Manufacturing","funder_award_id":"2218063","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3768993770","display_name":"Reflexive robotics using asynchronous perception","funder_award_id":"EP/S035761/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415824654.pdf","grobid_xml":"https://content.openalex.org/works/W4415824654.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1938020354","https://openalex.org/W2199890863","https://openalex.org/W2963474852","https://openalex.org/W3035158519","https://openalex.org/W3081227581","https://openalex.org/W3179267034","https://openalex.org/W4312443924","https://openalex.org/W4319300728","https://openalex.org/W4382467090","https://openalex.org/W4388796689","https://openalex.org/W4390873434","https://openalex.org/W4393149524","https://openalex.org/W4401567700","https://openalex.org/W4404520490","https://openalex.org/W4408017267","https://openalex.org/W4409263874"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,131],"present":[4],"a":[5,93,98],"high-performing":[6],"solution":[7],"to":[8,22,41],"the":[9,27,70,78,107,119,127,154],"UAVM":[10],"2025":[11],"Challenge,":[12],"which":[13],"focuses":[14],"on":[15],"matching":[16],"narrow":[17],"Field-of-View":[18],"(FOV)":[19],"street-level":[20,52],"images":[21,60],"corresponding":[23],"satellite":[24,89],"imagery":[25],"using":[26],"University-1652":[28],"dataset.":[29],"As":[30],"panoramic":[31,51],"Cross-View":[32],"Geo-Localisation":[33],"nears":[34],"peak":[35],"performance,":[36],"it":[37],"becomes":[38],"increasingly":[39],"important":[40],"explore":[42],"more":[43,114],"practical":[44,164],"problem":[45],"formulations.":[46],"Real-world":[47],"scenarios":[48],"rarely":[49],"offer":[50],"queries;":[53],"instead,":[54],"queries":[55],"typically":[56],"consist":[57],"of":[58,80,147,156],"limited-FOV":[59],"captured":[61],"with":[62],"unknown":[63],"camera":[64],"parameters.":[65],"Our":[66,83],"work":[67],"prioritises":[68],"discovering":[69],"highest":[71],"achievable":[72],"performance":[73],"under":[74,118],"these":[75],"constraints,":[76],"pushing":[77],"limits":[79],"existing":[81],"architectures.":[82],"method":[84],"begins":[85],"by":[86,97],"retrieving":[87],"candidate":[88],"image":[90],"embeddings":[91],"for":[92],"given":[94],"query,":[95],"followed":[96],"re-ranking":[99,160],"stage":[100],"that":[101,133],"selectively":[102],"enhances":[103],"retrieval":[104,145,158],"accuracy":[105],"within":[106],"top":[108],"candidates.":[109],"This":[110,152],"two-stage":[111],"approach":[112,135],"enables":[113],"precise":[115],"matching,":[116],"even":[117],"significant":[120],"viewpoint":[121],"and":[122,143,149,159],"scale":[123],"variations":[124],"inherent":[125],"in":[126,162],"task.":[128],"Through":[129],"experimentation,":[130],"demonstrate":[132],"our":[134],"achieves":[136],"competitive":[137],"results":[138],"-":[139],"specifically":[140],"attaining":[141],"R@1":[142],"R@10":[144],"rates":[146],"30.21%":[148],"63.13%":[150],"respectively.":[151],"underscores":[153],"potential":[155],"optimised":[157],"strategies":[161],"advancing":[163],"geo-localisation":[165],"performance.":[166],"Code":[167],"is":[168],"available":[169],"at":[170],"github.com/tavisshore/VICI.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-03T00:00:00"}