{"id":"https://openalex.org/W4409959339","doi":"https://doi.org/10.1007/s44267-025-00078-x","title":"Uncertainty-aware coarse-to-fine alignment for text-image person retrieval","display_name":"Uncertainty-aware coarse-to-fine alignment for text-image person retrieval","publication_year":2025,"publication_date":"2025-04-29","ids":{"openalex":"https://openalex.org/W4409959339","doi":"https://doi.org/10.1007/s44267-025-00078-x"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00078-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00078-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00078-x.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00078-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032010578","display_name":"Yi\u2010Fei Deng","orcid":"https://orcid.org/0009-0004-5906-7565"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifei Deng","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101886931","display_name":"Zhengyu Chen","orcid":"https://orcid.org/0000-0002-9567-5881"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyu Chen","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, 230601, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, 230601, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030720334","display_name":"Jin Tang","orcid":"https://orcid.org/0000-0001-8375-3590"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Tang","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032010578"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":5.8575,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96049395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9993000030517578,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9993000030517578,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.991100013256073,"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/T11448","display_name":"Face recognition and analysis","score":0.9830999970436096,"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":0.6071935892105103},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5281028151512146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5109916925430298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5019583702087402},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43772539496421814},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42532384395599365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3311237692832947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6071935892105103},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5281028151512146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5109916925430298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5019583702087402},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43772539496421814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42532384395599365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3311237692832947}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-025-00078-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00078-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00078-x.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bb85943bfd664837bf8e0b3b27d9d96c","is_oa":true,"landing_page_url":"https://doaj.org/article/bb85943bfd664837bf8e0b3b27d9d96c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00078-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00078-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00078-x.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5471173546","display_name":null,"funder_award_id":"2022-03","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G845944294","display_name":null,"funder_award_id":"62376004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G849060900","display_name":null,"funder_award_id":"2208085J18","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409959339.pdf","grobid_xml":"https://content.openalex.org/works/W4409959339.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2143017621","https://openalex.org/W2209877316","https://openalex.org/W2602856279","https://openalex.org/W2604292070","https://openalex.org/W2743355020","https://openalex.org/W2769994766","https://openalex.org/W2801814609","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2963188742","https://openalex.org/W2982281627","https://openalex.org/W2997421053","https://openalex.org/W3025623188","https://openalex.org/W3094502228","https://openalex.org/W3099681648","https://openalex.org/W3135367836","https://openalex.org/W3141362964","https://openalex.org/W3147954272","https://openalex.org/W3187284461","https://openalex.org/W3206868111","https://openalex.org/W4236965008","https://openalex.org/W4292420219","https://openalex.org/W4301409532","https://openalex.org/W4304087170","https://openalex.org/W4305028645","https://openalex.org/W4309520117","https://openalex.org/W4312998013","https://openalex.org/W4360834502","https://openalex.org/W4386556594","https://openalex.org/W4386758381","https://openalex.org/W4386875720","https://openalex.org/W4387968073","https://openalex.org/W4387969570","https://openalex.org/W4388145471","https://openalex.org/W4392693793","https://openalex.org/W6608406338","https://openalex.org/W6640963894","https://openalex.org/W6678984984","https://openalex.org/W6734337038","https://openalex.org/W6775547499","https://openalex.org/W6788213132"],"related_works":["https://openalex.org/W2087793626","https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344"],"abstract_inverted_index":{"Abstract":[0],"Text-to-image":[1],"person":[2,13,27,121,207],"retrieval,":[3,208],"a":[4,21,88,115],"fine-grained":[5,202,221],"cross-modal":[6,191],"retrieval":[7,28,80],"problem,":[8,85],"aims":[9],"to":[10,34,54,72,78,99,139],"search":[11],"for":[12,68,118],"images":[14,61],"from":[15],"an":[16],"image":[17],"library":[18],"that":[19,152],"match":[20],"given":[22],"textual":[23],"caption.":[24],"Existing":[25],"text-to-image":[26,120,206],"methods":[29,71],"usually":[30],"use":[31],"fixed-point":[32,69,97],"embedding":[33,50,70,98],"express":[35],"the":[36,39,49,55,155,175,196,201,211,229,246],"semantics":[37],"of":[38,109,131,178,198,205,213,249],"two":[40,105,127,242],"modalities":[41,47,106,164],"and":[42,62,102,111,135,180,189,231],"perform":[43],"multi-granularity":[44],"alignment":[45,92,143,222],"between":[46,60],"in":[48,107,228],"space.":[51],"However,":[52],"owing":[53],"inherent":[56],"mutual":[57],"one-to-many":[58],"correspondence":[59],"texts,":[63],"it":[64],"is":[65],"often":[66],"difficult":[67],"adequately":[73],"capture":[74],"this":[75,84],"relationship,":[76],"leading":[77],"erroneous":[79],"results.":[81],"To":[82],"address":[83],"we":[86,124,209],"propose":[87],"novel":[89],"uncertainty-aware":[90,214],"coarse-to-fine":[91,116],"method,":[93],"which":[94,184,219],"first":[95,125],"maps":[96],"probability":[100],"distributions":[101,110,153],"then":[103],"aligns":[104],"terms":[108],"sampling":[112,182],"points":[113],"at":[114],"granularity,":[117],"accurate":[119],"retrieval.":[122],"Specifically,":[123],"introduce":[126],"contrastive":[128,167,176],"learning":[129,134,149,172,177,197],"tasks":[130],"distribution":[132,147],"contrast":[133,137,148,171],"point":[136,170,237],"learning,":[138],"achieve":[140],"coarse-grained":[141],"inter-modal":[142,179,235],"with":[144,154],"uncertainty-aware.":[145],"The":[146,169],"task":[150,173,212],"ensures":[151],"same":[156],"identity":[157],"are":[158],"as":[159,161],"similar":[160],"possible":[162],"across":[163],"through":[165],"distribution-based":[166],"learning.":[168],"performs":[174],"intra-modal":[181],"points,":[183],"not":[185],"only":[186],"models":[187],"rich":[188],"diverse":[190],"associations,":[192],"but":[193],"also":[194],"optimizes":[195],"distributions.":[199],"For":[200],"association":[203],"requirements":[204],"design":[210],"attribute":[215,226],"masking":[216,225],"language":[217],"reconstruction,":[218],"achieves":[220],"by":[223],"randomly":[224],"words":[227],"text":[230],"reconstructing":[232],"them":[233],"via":[234],"sample":[236],"interactions.":[238],"Extensive":[239],"experiments":[240],"on":[241],"public":[243],"datasets":[244],"demonstrate":[245],"superior":[247],"performance":[248],"our":[250],"method.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}