{"id":"https://openalex.org/W4415428910","doi":"https://doi.org/10.3233/faia250873","title":"GEA: Generation-Enhanced Alignment for Text-to-Image Person Retrieval","display_name":"GEA: Generation-Enhanced Alignment for Text-to-Image Person Retrieval","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428910","doi":"https://doi.org/10.3233/faia250873"},"language":null,"primary_location":{"id":"doi:10.3233/faia250873","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250873","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100523070","display_name":"Hao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Zou","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084505306","display_name":"Runqing Zhang","orcid":"https://orcid.org/0000-0002-0503-7254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runqing Zhang","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022203746","display_name":"Xue Zhou","orcid":"https://orcid.org/0000-0002-6569-9524"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Zhou","raw_affiliation_strings":["School of Automation Engineering, University of Electronic Science and Technology of China","Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"School of Automation Engineering, University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027642367","display_name":"Jianxiao Zou","orcid":"https://orcid.org/0000-0002-8676-8322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianxiao Zou","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100523070"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67492142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.984499990940094,"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":0.984499990940094,"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":0.954200029373169,"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/T11439","display_name":"Video Analysis and Summarization","score":0.928600013256073,"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/overfitting","display_name":"Overfitting","score":0.7778000235557556},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5972999930381775},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5719000101089478},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5339999794960022},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4869999885559082},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4643999934196472},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4523000121116638},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.444599986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251000046730042},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7778000235557556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330999732017517},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5972999930381775},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5719000101089478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4523000121116638},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia250873","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250873","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2511.10154","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10154","pdf_url":"https://arxiv.org/pdf/2511.10154","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"doi:10.3233/faia250873","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250873","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"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/G2125056091","display_name":null,"funder_award_id":"JCYJ20240813114206010","funder_id":"https://openalex.org/F4320316880","funder_display_name":"Natural Science Foundation of Shenzhen City"},{"id":"https://openalex.org/G2373308536","display_name":null,"funder_award_id":"62372082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","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/G3757194791","display_name":null,"funder_award_id":"JCYJ20","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"}],"funders":[{"id":"https://openalex.org/F4320316880","display_name":"Natural Science Foundation of Shenzhen City","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-Image":[0],"Person":[1],"Retrieval":[2],"(TIPR)":[3],"aims":[4],"to":[5,36,42,97,136,159],"retrieve":[6],"person":[7],"images":[8,92,108],"based":[9],"on":[10,150],"natural":[11],"language":[12],"descriptions.":[13],"Although":[14],"many":[15],"TIPR":[16,153],"methods":[17],"have":[18],"achieved":[19],"promising":[20],"results,":[21],"sometimes":[22],"textual":[23],"queries":[24],"cannot":[25],"accurately":[26],"and":[27,40,52,103,115,133,157,177],"comprehensively":[28],"reflect":[29],"the":[30,33,46,71,99,110,161,169],"content":[31],"of":[32,113,163,171],"image,":[34],"leading":[35],"poor":[37],"cross-modal":[38,60,117],"alignment":[39,144],"overfitting":[41],"limited":[43],"datasets.":[44],"Moreover,":[45],"inherent":[47],"modality":[48],"gap":[49,100],"between":[50,101,128],"text":[51,102,114,134],"image":[53],"further":[54],"amplifies":[55],"these":[56,67],"issues,":[57],"making":[58],"accurate":[59],"retrieval":[61],"even":[62],"more":[63],"challenging.":[64],"To":[65],"address":[66],"limitations,":[68],"we":[69],"propose":[70],"Generation-Enhanced":[72],"Alignment":[73],"(GEA)":[74],"from":[75],"a":[76,138],"generative":[77],"perspective.":[78],"GEA":[79],"contains":[80],"two":[81],"parallel":[82],"modules:":[83],"1)":[84],"Text-Guided":[85],"Token":[86],"Enhancement":[87],"(TGTE),":[88],"which":[89,125],"introduces":[90],"diffusion-generated":[91],"as":[93],"intermediate":[94],"semantic":[95,111],"representations":[96],"bridge":[98],"visual":[104],"patterns.":[105],"These":[106],"generated":[107,129],"enrich":[109],"representation":[112,140],"facilitate":[116],"alignment.":[118],"2)":[119],"Generative":[120],"Intermediate":[121],"Fusion":[122],"(GIF)":[123],"module,":[124],"combines":[126],"cross-attention":[127],"images,":[130,132],"original":[131],"features":[135],"generate":[137],"unified":[139],"optimized":[141],"by":[142],"triplet":[143],"loss.":[145],"We":[146],"conduct":[147],"extensive":[148],"experiments":[149],"three":[151],"public":[152],"datasets,":[154],"CUHK-PEDES,":[155],"RSTPReid,":[156],"ICFG-PEDES,":[158],"evaluate":[160],"performance":[162],"GEA.":[164],"The":[165],"remarkable":[166],"results":[167,179],"justify":[168],"efficacy":[170],"our":[172],"method.":[173],"More":[174],"implementation":[175],"details":[176],"extended":[178],"are":[180],"available":[181],"at":[182],"https://github.com/sugelamyd123/Sup-for-GEA.":[183]},"counts_by_year":[],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-23T00:00:00"}