{"id":"https://openalex.org/W4412825778","doi":"https://doi.org/10.1145/3711896.3737141","title":"Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework","display_name":"Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412825778","doi":"https://doi.org/10.1145/3711896.3737141"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014939822","display_name":"Xiao Han","orcid":"https://orcid.org/0000-0002-3478-964X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao Han","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China and Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3478-964X","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China and Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768322","display_name":"Chen Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4817-482X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049015446","display_name":"Hengshu Zhu","orcid":"https://orcid.org/0000-0003-4570-643X"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengshu Zhu","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4570-643X","affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2926-4416","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"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":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81291537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"814","last_page":"825"},"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":0.9965000152587891,"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":0.9965000152587891,"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":0.9914000034332275,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7398453950881958},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"Swarm intelligence","score":0.5619633197784424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573983192443848},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.484826922416687},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39618292450904846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3649464249610901},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33955317735671997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21109092235565186},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.13117611408233643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398453950881958},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.5619633197784424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573983192443848},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.484826922416687},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39618292450904846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3649464249610901},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33955317735671997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21109092235565186},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.13117611408233643}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2322073474","https://openalex.org/W2737075200","https://openalex.org/W2884148180","https://openalex.org/W2886604692","https://openalex.org/W2895392434","https://openalex.org/W2914993068","https://openalex.org/W2963588253","https://openalex.org/W2984478347","https://openalex.org/W2999585771","https://openalex.org/W3011305631","https://openalex.org/W3015451023","https://openalex.org/W3023735075","https://openalex.org/W3033175466","https://openalex.org/W3034213661","https://openalex.org/W3095367607","https://openalex.org/W3163149666","https://openalex.org/W3206622090","https://openalex.org/W3215715903","https://openalex.org/W4223541729","https://openalex.org/W4225323218","https://openalex.org/W4286896674","https://openalex.org/W4298222326","https://openalex.org/W4312854990","https://openalex.org/W4385571184","https://openalex.org/W4398859520","https://openalex.org/W4404782367","https://openalex.org/W4409369514","https://openalex.org/W6600339457"],"related_works":["https://openalex.org/W4308079021","https://openalex.org/W1527337688","https://openalex.org/W2399799070","https://openalex.org/W2746377055","https://openalex.org/W4386001959","https://openalex.org/W2594296178","https://openalex.org/W3089846858","https://openalex.org/W4304182880","https://openalex.org/W3012322385","https://openalex.org/W2159541481"],"abstract_inverted_index":{"Visual":[0,47],"geo-localization":[1,45,89],"demands":[2],"in-depth":[3],"knowledge":[4,75,110],"and":[5,76,140,160],"advanced":[6],"reasoning":[7,77],"skills":[8],"to":[9,121],"associate":[10],"images":[11],"with":[12,114],"precise":[13],"real-world":[14],"geo-graphic":[15],"locations.":[16],"Existing":[17],"image":[18,60],"database":[19],"retrieval":[20],"methods":[21],"are":[22],"limited":[23,71],"by":[24,72],"the":[25,42,63,108,119,147,150,161],"impracticality":[26],"of":[27,32,44,65,111,149],"storing":[28],"sufficient":[29],"visual":[30,88],"records":[31],"global":[33],"landmarks.":[34],"Recently,":[35],"Large":[36],"Vision-Language":[37],"Models":[38],"(LVLMs)":[39],"have":[40],"demonstrated":[41],"capability":[43],"through":[46],"Question":[48],"Answering":[49],"(VQA),":[50],"enabling":[51],"a":[52,66,86,129],"solution":[53],"that":[54,91,133,164],"does":[55],"not":[56],"require":[57],"external":[58],"geo-tagged":[59],"records.":[61],"However,":[62],"performance":[64],"single":[67],"LVLM":[68,95],"is":[69,175],"still":[70],"its":[73],"intrinsic":[74],"capabilities.":[78],"To":[79,145],"address":[80],"these":[81,112],"challenges,":[82],"we":[83,153],"introduce":[84],"smileGeo,":[85],"novel":[87],"framework":[90,127],"leverages":[92],"multiple":[93],"Internet-enabled":[94],"agents":[96,113],"operating":[97],"within":[98],"an":[99],"agent-based":[100],"architecture.":[101],"By":[102],"facilitating":[103],"inter-agent":[104],"communication,":[105,136],"smileGeo":[106],"integrates":[107],"inherent":[109],"additional":[115],"retrieved":[116],"information,":[117],"enhancing":[118,141],"ability":[120],"effectively":[122],"localize":[123],"images.":[124],"Furthermore,":[125],"our":[126,165],"incorporates":[128],"dynamic":[130],"learning":[131],"strategy":[132],"optimizes":[134],"agent":[135],"reducing":[137],"redundant":[138],"interactions":[139],"overall":[142],"system":[143],"efficiency.":[144],"validate":[146],"effectiveness":[148],"proposed":[151],"framework,":[152],"conducted":[154],"experiments":[155],"on":[156],"three":[157],"different":[158],"datasets,":[159],"results":[162],"show":[163],"approach":[166],"significantly":[167],"outperforms":[168],"current":[169],"state-of-the-art":[170],"methods.":[171],"The":[172],"source":[173],"code":[174],"available":[176],"at":[177],"https://github.com/Applied-Machine-Learning-Lab/smileGeo.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}