{"id":"https://openalex.org/W4383750862","doi":"https://doi.org/10.1109/tcsvt.2023.3293514","title":"DeHi: A Decoupled Hierarchical Architecture for Unaligned Ground-to-Aerial Geo-Localization","display_name":"DeHi: A Decoupled Hierarchical Architecture for Unaligned Ground-to-Aerial Geo-Localization","publication_year":2023,"publication_date":"2023-07-10","ids":{"openalex":"https://openalex.org/W4383750862","doi":"https://doi.org/10.1109/tcsvt.2023.3293514"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3293514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3293514","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5101506354","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0002-1802-0435"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Teng Wang","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1802-0435","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331442","display_name":"Jiawen Li","orcid":"https://orcid.org/0000-0002-5917-385X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Li","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5917-385X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101506354"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":1.642,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86002399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"3","first_page":"1927","last_page":"1940"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.735404372215271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.62442547082901},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5671018958091736},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.509367823600769},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4688469171524048},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.45847442746162415},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45542046427726746},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4403148591518402},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.43343502283096313},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4306226670742035},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42749476432800293},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.42660757899284363},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4206918776035309},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4192243814468384},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41130760312080383},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32121628522872925},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1754847764968872},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13453909754753113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735404372215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62442547082901},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5671018958091736},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.509367823600769},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4688469171524048},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.45847442746162415},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45542046427726746},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4403148591518402},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43343502283096313},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4306226670742035},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42749476432800293},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.42660757899284363},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4206918776035309},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4192243814468384},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41130760312080383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32121628522872925},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1754847764968872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13453909754753113},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3293514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3293514","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5686492328","display_name":null,"funder_award_id":"62273093","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1938020354","https://openalex.org/W1946093182","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2199890863","https://openalex.org/W2340690086","https://openalex.org/W2479919622","https://openalex.org/W2565639579","https://openalex.org/W2572697301","https://openalex.org/W2799087793","https://openalex.org/W2946492178","https://openalex.org/W2962858109","https://openalex.org/W2963474852","https://openalex.org/W2963588253","https://openalex.org/W2964157791","https://openalex.org/W2981670313","https://openalex.org/W2992077842","https://openalex.org/W2997129483","https://openalex.org/W3016713745","https://openalex.org/W3035158519","https://openalex.org/W3081227581","https://openalex.org/W3100623370","https://openalex.org/W3109923227","https://openalex.org/W3110536152","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3160550216","https://openalex.org/W3174873881","https://openalex.org/W3185141858","https://openalex.org/W3188851454","https://openalex.org/W3205797353","https://openalex.org/W3212436340","https://openalex.org/W3212645988","https://openalex.org/W4205474609","https://openalex.org/W4212833811","https://openalex.org/W4214493665","https://openalex.org/W4282937133","https://openalex.org/W4312703192","https://openalex.org/W4319300073","https://openalex.org/W6637373629","https://openalex.org/W6638556758","https://openalex.org/W6679792166","https://openalex.org/W6757817989","https://openalex.org/W6761621725","https://openalex.org/W6788135285","https://openalex.org/W6790545018","https://openalex.org/W6803850277","https://openalex.org/W6932051444"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2807634898","https://openalex.org/W1692008701","https://openalex.org/W2942366970","https://openalex.org/W2597588799","https://openalex.org/W2047973478","https://openalex.org/W2032182853"],"abstract_inverted_index":{"Ground-to-aerial":[0],"(G2A)":[1],"geo-localization":[2],"remains":[3],"extremely":[4],"challenging":[5,33],"due":[6],"to":[7,50,70,81,102,121,141,169,203,209,232],"the":[8,32,40,111,131,138,143,171,191,197],"drastic":[9],"appearance":[10],"and":[11,16,63,86,98,105,124,130,206,214],"geometry":[12],"differences":[13],"between":[14],"ground":[15],"aerial":[17,52],"views,":[18],"especially":[19],"when":[20],"their":[21],"relative":[22],"orientation":[23,220],"is":[24,44,135],"unknown.":[25],"In":[26],"this":[27,56],"paper,":[28],"we":[29],"focus":[30],"on":[31,179,212],"problem":[34,57],"of":[35,96,113],"unaligned":[36],"G2A":[37],"geo-localization,":[38],"where":[39],"query":[41,145],"ground-level":[42],"image":[43],"not":[45],"perfectly":[46],"orientation-aligned":[47],"with":[48,137,165,190,228],"respect":[49],"reference":[51],"imagery.":[53],"We":[54,159],"cast":[55],"as":[58],"a":[59,65,89,149],"metric":[60],"embedding":[61],"task":[62],"propose":[64],"decoupled":[66,150],"hierarchical":[67,151],"(DeHi)":[68],"architecture":[69,152],"progressively":[71],"learn":[72,103],"meaningful":[73],"multi-grained":[74],"features.":[75],"Specifically,":[76],"DeHi":[77,195,223],"first":[78],"leverages":[79],"CNN":[80,128],"extract":[82],"high-level":[83],"semantic":[84],"features,":[85,129],"then":[87],"introduces":[88],"novel":[90],"orthogonally":[91],"factorized":[92],"transformer":[93,100],"model":[94],"consisting":[95],"part-level":[97,104,123,133,162],"global":[99,106,125,139,174],"encoders":[101],"feature":[107],"descriptors":[108,126],"sequentially.":[109],"For":[110],"purpose":[112],"enhancing":[114],"representation":[115],"power,":[116],"cross-level":[117,167],"connections":[118],"are":[119],"introduced":[120],"enrich":[122],"by":[127],"pooled":[132],"descriptor":[134,140],"combined":[136,164],"construct":[142],"final":[144],"representation.":[146],"Furthermore,":[147],"such":[148],"allows":[153],"for":[154],"incorporating":[155],"multi-level":[156],"deep":[157],"supervision.":[158],"introduce":[160],"two":[161],"losses":[163],"one":[166],"loss":[168],"complement":[170],"widely":[172],"used":[173],"retrieval":[175],"loss.":[176],"Extensive":[177],"experiments":[178],"standard":[180],"benchmark":[181],"datasets":[182],"show":[183],"significant":[184],"boosting":[185],"in":[186],"recall":[187,198],"rates":[188],"compared":[189,231],"previous":[192],"state-of-the-art.":[193],"Remarkably,":[194],"improves":[196],"rate":[199],"@top-1":[200],"from":[201,207],"78.59%":[202],"82.38%":[204],"(+3.79%)":[205],"72.91%":[208],"77.94%":[210],"(+5.03%)":[211],"CVUSA":[213],"CVACT":[215],"datasets,":[216],"respectively,":[217],"under":[218],"random":[219],"misalignments.":[221],"Besides,":[222],"maintains":[224],"competitive":[225],"inference":[226],"efficiency":[227],"less":[229],"parameters":[230],"existing":[233],"transformer-based":[234],"methods.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}