{"id":"https://openalex.org/W4416237737","doi":"https://doi.org/10.1109/wacv61042.2026.00063","title":"From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance","display_name":"From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416237737","doi":"https://doi.org/10.1109/wacv61042.2026.00063"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00063","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/2511.09820","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102870075","display_name":"Jeongho Min","orcid":"https://orcid.org/0009-0005-6731-3137"},"institutions":[{"id":"https://openalex.org/I4210111579","display_name":"Lumir Research Institute (United States)","ror":"https://ror.org/01ydcrt14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210111579"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeongho Min","raw_affiliation_strings":["Lumir Inc.,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lumir Inc.,South Korea","institution_ids":["https://openalex.org/I4210111579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357421","display_name":"Dongyoung Kim","orcid":"https://orcid.org/0000-0002-3364-6524"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongyoung Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI),South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI),South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002247218","display_name":"Jaehyup Lee","orcid":"https://orcid.org/0000-0002-2137-2650"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyup Lee","raw_affiliation_strings":["Kyungpook National University,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University,South Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01858098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"579"},"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":0.6035000085830688,"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":0.6035000085830688,"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/T13282","display_name":"Automated Road and Building Extraction","score":0.1932000070810318,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.04769999906420708,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/pipeline","display_name":"Pipeline (software)","score":0.6413000226020813},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6226999759674072},{"id":"https://openalex.org/keywords/geocoding","display_name":"Geocoding","score":0.6004999876022339},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.586899995803833},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5629000067710876},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5241000056266785},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5084999799728394},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.450300008058548},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43149998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170999884605408},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281999945640564},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C42629822","wikidata":"https://www.wikidata.org/wiki/Q1346408","display_name":"Geocoding","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47369998693466187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C53605480","wikidata":"https://www.wikidata.org/wiki/Q852595","display_name":"Geotagging","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00063","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:2511.09820","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.09820","pdf_url":"https://arxiv.org/pdf/2511.09820","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.2511.09820","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.09820","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:2511.09820","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.09820","pdf_url":"https://arxiv.org/pdf/2511.09820","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":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-view":[0],"image":[1,54,85],"retrieval,":[2],"particularly":[3],"street-to-satellite":[4,144],"matching,":[5],"is":[6,147],"a":[7,49,59,64,74,92,103,149],"critical":[8],"task":[9],"for":[10],"applications":[11],"such":[12],"as":[13],"autonomous":[14],"navigation,":[15],"urban":[16],"planning,":[17],"and":[18,33,63,87,98,151],"localization":[19],"in":[20],"GPS-denied":[21],"environments.":[22],"However,":[23],"existing":[24],"approaches":[25,127],"often":[26],"require":[27],"supervised":[28],"training":[29],"on":[30,35,128],"curated":[31],"datasets":[32],"rely":[34],"panoramic":[36],"or":[37,119],"UAV-based":[38],"images,":[39],"which":[40,146],"limits":[41],"real-world":[42],"deployment.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"present":[48],"simple":[50],"yet":[51],"effective":[52],"cross-view":[53],"retrieval":[55],"framework":[56],"that":[57],"leverages":[58],"pretrained":[60,104],"vision":[61,105],"encoder":[62,106],"large":[65],"language":[66],"model":[67],"(LLM),":[68],"requiring":[69],"no":[70],"additional":[71],"training.":[72],"Given":[73],"monocular":[75],"street-view":[76],"image,":[77],"our":[78,121,136],"method":[79,123],"extracts":[80],"geographic":[81],"cues":[82],"through":[83],"web-based":[84],"search":[86],"LLM-based":[88],"location":[89],"inference,":[90],"generates":[91],"satellite":[93],"query":[94],"via":[95],"geocoding":[96],"API,":[97],"retrieves":[99],"matching":[100],"tiles":[101],"using":[102,116],"(e.g.,":[107],"DINOv2)":[108],"with":[109],"PCA-based":[110],"whitening":[111],"feature":[112],"refinement.":[113],"Despite":[114],"not":[115],"ground-truth":[117],"supervision":[118],"finetuning,":[120],"proposed":[122],"outperforms":[124],"prior":[125],"learning-based":[126],"the":[129],"benchmark":[130],"dataset":[131],"under":[132],"zero-shot":[133],"settings.":[134],"Moreover,":[135],"pipeline":[137],"enables":[138],"automatic":[139],"construction":[140],"of":[141],"semantically":[142],"aligned":[143],"datasets,":[145],"offering":[148],"scalable":[150],"cost-efficient":[152],"alternative":[153],"to":[154],"manual":[155],"annotation.":[156],"All":[157],"source":[158],"codes":[159],"will":[160],"be":[161],"made":[162],"publicly":[163],"available":[164],"at":[165],"https://jeonghomin.github.io/":[166],"street2orbit.github.io/.":[167]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-11-15T00:00:00"}