{"id":"https://openalex.org/W4415539516","doi":"https://doi.org/10.1145/3746027.3755171","title":"Unsupervised Cross-Modal Person Search via Progressive Diverse Text Generation","display_name":"Unsupervised Cross-Modal Person Search via Progressive Diverse Text Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539516","doi":"https://doi.org/10.1145/3746027.3755171"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5049386102","display_name":"F.H.Y. Chen","orcid":"https://orcid.org/0000-0002-8946-0083"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Anhui University of Technology, Ma'anshan, China"],"raw_orcid":"https://orcid.org/0000-0002-8946-0083","affiliations":[{"raw_affiliation_string":"Anhui University of Technology, Ma'anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132116","display_name":"Jielong He","orcid":null},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielong He","raw_affiliation_strings":["Anhui University of Technology, Ma'anshan, China"],"raw_orcid":"https://orcid.org/0009-0003-6676-1902","affiliations":[{"raw_affiliation_string":"Anhui University of Technology, Ma'anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Liu","orcid":"https://orcid.org/0009-0004-5905-0974"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Anhui university of technology, Ma'anshan, China"],"raw_orcid":"https://orcid.org/0009-0004-5905-0974","affiliations":[{"raw_affiliation_string":"Anhui university of technology, Ma'anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753323","display_name":"Heng Liu","orcid":"https://orcid.org/0000-0001-7563-2676"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Liu","raw_affiliation_strings":["AnHui University of Technology, Ma'anshan, China"],"raw_orcid":"https://orcid.org/0000-0001-7563-2676","affiliations":[{"raw_affiliation_string":"AnHui University of Technology, Ma'anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhe Chen","orcid":"https://orcid.org/0009-0008-7877-8775"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["Anhui University of Technology, Ma'anshan, China"],"raw_orcid":"https://orcid.org/0009-0008-7877-8775","affiliations":[{"raw_affiliation_string":"Anhui University of Technology, Ma'anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6596-8117","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6047","last_page":"6056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9889000058174133,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9889000058174133,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9729999899864197,"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":0.9300000071525574,"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/annotation","display_name":"Annotation","score":0.6061999797821045},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.42559999227523804},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.41040000319480896},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.39430001378059387},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.37369999289512634},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804099977016449},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586899995803833},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47279998660087585},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.42559999227523804},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37869998812675476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2840000092983246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2832756618","display_name":null,"funder_award_id":"62206006; 62302140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5784255744","display_name":null,"funder_award_id":"JZ2024HGTB0261","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"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":30,"referenced_works":["https://openalex.org/W2609731892","https://openalex.org/W2963449390","https://openalex.org/W2963882743","https://openalex.org/W2965848243","https://openalex.org/W3088460296","https://openalex.org/W3189221782","https://openalex.org/W3206868111","https://openalex.org/W4214770152","https://openalex.org/W4283818632","https://openalex.org/W4297821751","https://openalex.org/W4297833440","https://openalex.org/W4315475891","https://openalex.org/W4380434649","https://openalex.org/W4386065462","https://openalex.org/W4386075661","https://openalex.org/W4387968135","https://openalex.org/W4387969466","https://openalex.org/W4387969591","https://openalex.org/W4388145471","https://openalex.org/W4389331836","https://openalex.org/W4389331911","https://openalex.org/W4390970441","https://openalex.org/W4392251567","https://openalex.org/W4393148792","https://openalex.org/W4393153810","https://openalex.org/W4394585954","https://openalex.org/W4395069639","https://openalex.org/W4395659479","https://openalex.org/W4402703029","https://openalex.org/W4410636438"],"related_works":[],"abstract_inverted_index":{"While":[0],"text-based":[1,166],"person":[2,55,167],"search":[3,56,168],"(TBPS)":[4],"has":[5],"achieved":[6],"notable":[7],"progress":[8],"in":[9,110,161],"recent":[10],"years,":[11],"existing":[12],"methods":[13],"heavily":[14],"rely":[15],"on":[16],"laboriously":[17],"annotated":[18],"and":[19,85,100,124,149],"well-aligned":[20],"pedestrian":[21],"image-text":[22],"pairs,":[23],"incurring":[24],"prohibitive":[25],"annotation":[26],"costs.":[27],"To":[28,45],"overcome":[29],"this":[30,47],"limitation,":[31],"we":[32,50],"propose":[33,51],"to":[34,104,120,135],"train":[35],"a":[36,150],"TBPS":[37],"model":[38],"using":[39],"pure":[40],"images":[41],"without":[42],"any":[43],"annotations.":[44],"tackle":[46],"challenging":[48],"problem,":[49],"an":[52],"unsupervised":[53,162],"cross-modal":[54,126],"framework":[57],"via":[58],"Progressive":[59,75],"Diverse":[60,76],"Text":[61,77],"Generation":[62,78],"(PSPD),":[63],"leveraging":[64],"large":[65,117],"pre-trained":[66],"models":[67,119],"as":[68],"assistants.":[69],"Particularly,":[70],"PSPD":[71],"features":[72],"three":[73],"modules:":[74],"(PDTG),":[79],"Fine-grained":[80],"Saliency":[81],"Region":[82],"Alignment":[83],"(FSRA)":[84],"Cross-Modal":[86],"pseudo":[87,137],"Label":[88],"Correction":[89],"(CMLC),":[90],"allowing":[91],"training":[92],"with":[93,146],"only":[94],"unannotated":[95],"images.":[96],"The":[97,113],"PDTG":[98],"generates":[99],"dynamically":[101],"adjusts":[102],"prompts":[103],"produce":[105],"accurate,":[106],"diverse":[107],"textual":[108],"descriptions":[109],"multiple":[111],"styles.":[112],"FSRA":[114],"then":[115],"uses":[116],"language":[118],"generate":[121],"fine-grained":[122,127],"attributes":[123],"achieves":[125],"semantic":[128],"alignment.":[129],"Additionally,":[130],"the":[131,156],"CMLC":[132],"is":[133,172],"applied":[134],"eliminate":[136],"label":[138],"noise":[139],"through":[140],"dual":[141],"mutual":[142],"nearest-neighbor":[143],"matching,":[144],"combined":[145],"distance-based":[147],"judgment":[148],"voting":[151],"mechanism.":[152],"Experimental":[153],"results":[154],"demonstrate":[155],"effectiveness":[157],"of":[158],"our":[159],"method":[160],"settings":[163],"across":[164],"various":[165],"datasets.":[169],"Source":[170],"code":[171],"at":[173],"https://github.com/flychen321/PSPD.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}