{"id":"https://openalex.org/W7156352777","doi":"https://doi.org/10.1145/3774904.3792233","title":"Augmenting Cross-View Geo-Localization with Spatial Semantics from Vision Foundation Models","display_name":"Augmenting Cross-View Geo-Localization with Spatial Semantics from Vision Foundation Models","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7156352777","doi":"https://doi.org/10.1145/3774904.3792233"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792233","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792233","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134661204","display_name":"Ji Shen","orcid":"https://orcid.org/0000-0002-3003-6237"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Shen","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3003-6237","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085364987","display_name":"Lixing Chen","orcid":"https://orcid.org/0000-0002-1805-0183"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixing Chen","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1805-0183","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039309279","display_name":"Yang Bai","orcid":"https://orcid.org/0000-0002-1037-3973"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Bai","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1037-3973","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069470446","display_name":"Zhongqi Miao","orcid":"https://orcid.org/0000-0002-0439-8592"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqi Miao","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8239-2727","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010329792","display_name":"Zhe Qu","orcid":"https://orcid.org/0000-0003-2211-2137"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Qu","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2211-2137","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8629-4622","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391361","display_name":"Jianhua Li","orcid":"https://orcid.org/0000-0002-6831-3973"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Li","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6831-3973","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5177","last_page":"5188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3497999906539917,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3497999906539917,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.32829999923706055,"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":0.07959999889135361,"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/semantics","display_name":"Semantics (computer science)","score":0.7008000016212463},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.588100016117096},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5582000017166138},{"id":"https://openalex.org/keywords/geometric-transformation","display_name":"Geometric transformation","score":0.5235000252723694},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5080999732017517},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4163999855518341},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.39480000734329224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021000027656555},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7008000016212463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989000201225281},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.5235000252723694},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48730000853538513},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.45509999990463257},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792233","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792233","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792233","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.8298432230949402,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1938020354","https://openalex.org/W1946093182","https://openalex.org/W2116341502","https://openalex.org/W2199890863","https://openalex.org/W2598199894","https://openalex.org/W2799087793","https://openalex.org/W2954174912","https://openalex.org/W2963474852","https://openalex.org/W3035158519","https://openalex.org/W3035749845","https://openalex.org/W3081227581","https://openalex.org/W3109395584","https://openalex.org/W3120013642","https://openalex.org/W3179267034","https://openalex.org/W3203158837","https://openalex.org/W4312443924","https://openalex.org/W4312703192","https://openalex.org/W4382467090","https://openalex.org/W4386632015","https://openalex.org/W4389872815","https://openalex.org/W4390873434","https://openalex.org/W4402733579","https://openalex.org/W4409263230","https://openalex.org/W4412900816"],"related_works":[],"abstract_inverted_index":{"Cross-view":[0],"geo-localization":[1],"(CVGL)":[2],"establishes":[3],"correspondences":[4],"between":[5],"ground-level":[6],"and":[7,29,56,65,80,91,117,134,191,204,212],"satellite":[8],"images":[9],"of":[10],"the":[11,122,143,147],"same":[12],"geographic":[13],"location,":[14],"serving":[15],"as":[16],"a":[17,77],"fundamental":[18],"technology":[19],"for":[20],"smart":[21],"city":[22],"applications,":[23],"including":[24,132],"autonomous":[25],"navigation,":[26],"urban":[27],"planning,":[28],"location-based":[30],"services.":[31],"Current":[32],"CVGL":[33,75,124,166],"approaches":[34,176],"fall":[35],"into":[36],"two":[37],"categories:":[38],"feature-based":[39,184],"methods":[40,52],"achieve":[41],"superior":[42],"performance":[43,180],"through":[44,200],"2D":[45],"representation":[46],"learning":[47],"but":[48,59],"lack":[49],"interpretability.":[50,213],"Spatial-based":[51],"provide":[53,197],"geometric":[54],"understanding":[55],"interpretable":[57],"matching":[58],"suffer":[60],"from":[61,76],"limited":[62],"spatial":[63,78,89,103,110,152],"modeling":[64],"weak":[66],"cross-view":[67],"alignment,":[68],"leading":[69],"to":[70,120,208],"lower":[71],"performance.":[72],"We":[73,99,196],"reformulate":[74],"perspective":[79],"propose":[81],"an":[82,101],"auxiliary":[83,102],"task-enhanced":[84],"network.":[85],"The":[86,126],"network":[87],"captures":[88,129],"semantics":[90],"provides":[92],"explicit":[93],"alignment":[94,105],"processes":[95],"with":[96,140,154,181],"visualizable":[97],"results.":[98],"introduce":[100],"semantic":[104],"(SSA)":[106],"task":[107,128,145],"that":[108,169],"learns":[109],"structure":[111,153],"via":[112],"vision":[113],"foundation":[114],"models":[115],"(VFM)":[116],"BEV":[118],"transformation":[119],"enhance":[121],"primary":[123,127,144],"task.":[125],"visual":[130,155],"semantics,":[131,156],"texture":[133],"appearance.":[135],"Within":[136],"this":[137],"unified":[138],"framework":[139],"shared":[141],"encoders,":[142],"enriches":[146],"learned":[148],"embeddings":[149],"by":[150],"fusing":[151],"yielding":[157],"spatially":[158],"complete":[159],"representations.":[160],"Extensive":[161],"experiments":[162],"on":[163,189,194],"three":[164],"standard":[165],"benchmarks":[167],"demonstrate":[168],"our":[170],"method":[171],"significantly":[172],"surpasses":[173],"previous":[174],"spatial-based":[175],"while":[177],"maintaining":[178],"competitive":[179],"state-of-the-art":[182],"(SOTA)":[183],"methods,":[185],"achieving":[186],"98.48%":[187],"R@1":[188,193],"CVUSA":[190],"71.05%":[192],"CVACT\\_test.":[195],"comprehensive":[198],"analyses":[199],"pixel-level":[201],"activation":[202],"maps":[203],"feature-space":[205],"UMAP":[206],"visualizations":[207],"validate":[209],"both":[210],"effectiveness":[211]},"counts_by_year":[],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2026-04-28T00:00:00"}