{"id":"https://openalex.org/W4399418404","doi":"https://doi.org/10.1145/3652583.3658054","title":"Fine-grained Semantics-aware Representation Learning for Text-based Person Retrieval","display_name":"Fine-grained Semantics-aware Representation Learning for Text-based Person Retrieval","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418404","doi":"https://doi.org/10.1145/3652583.3658054"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658054","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401389","display_name":"Di Wang","orcid":"https://orcid.org/0000-0001-8027-4287"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Di Wang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8027-4287","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036156519","display_name":"Feng Yan","orcid":"https://orcid.org/0009-0008-3035-835X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Yan","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0008-3035-835X","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101444711","display_name":"Yifeng Wang","orcid":"https://orcid.org/0000-0002-8425-2963"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Wang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-8425-2963","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039507264","display_name":"Lin Zhao","orcid":"https://orcid.org/0000-0001-6917-5966"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhao","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8756-2027","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101407402","display_name":"Liang Xiao","orcid":"https://orcid.org/0000-0003-0382-2715"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Liang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-0382-2715","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047277589","display_name":"Haodi Zhong","orcid":"https://orcid.org/0000-0001-6033-4959"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodi Zhong","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-6033-4959","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009723805","display_name":"Ronghua Zhang","orcid":"https://orcid.org/0000-0001-6004-6471"},"institutions":[{"id":"https://openalex.org/I102208913","display_name":"Shihezi University","ror":"https://ror.org/04x0kvm78","country_code":"CN","type":"education","lineage":["https://openalex.org/I102208913"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghua Zhang","raw_affiliation_strings":["Shihezi University, Shihezi, China"],"raw_orcid":"https://orcid.org/0000-0001-6004-6471","affiliations":[{"raw_affiliation_string":"Shihezi University, Shihezi, China","institution_ids":["https://openalex.org/I102208913"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100401389"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.3808,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8972168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.8235733509063721},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5759803056716919},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5670723915100098},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5605404376983643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.55698561668396},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5310379266738892},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.519696056842804},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4866676926612854},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4715440571308136},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46927300095558167},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4674540162086487},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4639570116996765},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42164623737335205},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4153297543525696},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08663034439086914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235733509063721},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5759803056716919},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5670723915100098},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5605404376983643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.55698561668396},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5310379266738892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.519696056842804},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4866676926612854},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4715440571308136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46927300095558167},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4674540162086487},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4639570116996765},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42164623737335205},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4153297543525696},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08663034439086914},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3272447550","display_name":null,"funder_award_id":"62072355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3301621070","display_name":null,"funder_award_id":"62072354","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7447316987","display_name":null,"funder_award_id":"QTZX23084","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8016219013","display_name":null,"funder_award_id":"62172222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320323230","display_name":"Xidian University","ror":"https://ror.org/05s92vm98"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418404.pdf","grobid_xml":"https://content.openalex.org/works/W4399418404.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2883311563","https://openalex.org/W2885722640","https://openalex.org/W2894786240","https://openalex.org/W2962964995","https://openalex.org/W2963449390","https://openalex.org/W2967515867","https://openalex.org/W2985951359","https://openalex.org/W2987861506","https://openalex.org/W3015686580","https://openalex.org/W3090449556","https://openalex.org/W3165835426","https://openalex.org/W3166304536","https://openalex.org/W3171668871","https://openalex.org/W3206776650","https://openalex.org/W3206868111","https://openalex.org/W4297833440","https://openalex.org/W4304087170","https://openalex.org/W4312533058","https://openalex.org/W4313181088","https://openalex.org/W4386065462","https://openalex.org/W4387969466","https://openalex.org/W4388145471","https://openalex.org/W4390874394"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W4390871823"],"abstract_inverted_index":{"Text-based":[0],"person":[1,62],"retrieval":[2],"aims":[3],"to":[4,59,142,155],"search":[5],"for":[6],"target":[7],"persons":[8,31],"based":[9],"on":[10,172,180],"a":[11,74,133],"given":[12],"text":[13,55,149],"description":[14],"query.":[15],"However,":[16],"existing":[17],"methods":[18],"often":[19],"have":[20],"the":[21,38,118,140,151,165,181],"following":[22],"problems:":[23],"(1)":[24],"Ignoring":[25],"local":[26,84,107],"attribute":[27,85,108],"information":[28],"between":[29,51,64],"different":[30,111],"in":[32,37,61,120,148],"feature":[33,44],"learning,":[34],"which":[35,57,100],"results":[36,171],"low":[39],"distinguishability":[40],"of":[41,128],"similar":[42],"people's":[43],"representations.":[45],"(2)":[46],"Lacking":[47],"fine-grained":[48,89,126,157],"semantics":[49],"alignment":[50],"visual":[52],"images":[53],"and":[54,66,87,176],"descriptions,":[56],"leads":[58],"inconsistency":[60],"details":[63],"query":[65],"target.":[67],"To":[68],"address":[69],"these":[70],"issues,":[71],"we":[72,93,131],"propose":[73,132],"<u>F</u>ine-grained":[75],"<u>S</u>emantics-aware":[76],"<u>R</u>epresentation":[77],"<u>L</u>earning":[78],"(<u>FSRL</u>)":[79],"method":[80,167],"that":[81,105,138,164],"establishing":[82],"intra-modal":[83],"correlations":[86],"inter-modal":[88],"semantic":[90,159],"correlations.":[91,160],"Specifically,":[92],"first":[94],"design":[95],"an":[96],"identity":[97,103,115],"self-distillation":[98],"module,":[99],"explores":[101],"soft":[102,114],"labels":[104,116],"reflect":[106],"similarities":[109],"among":[110],"people.":[112],"The":[113],"assist":[117],"model":[119,141],"learning":[121],"discriminative":[122],"features":[123],"associated":[124],"with":[125],"attributes":[127],"persons.":[129],"Secondly,":[130],"visual-language":[134],"relationship":[135],"modeling":[136],"module":[137],"enforces":[139],"proofread":[143],"\"error":[144],"words\"":[145],"randomly":[146],"changed":[147],"during":[150],"cross-modal":[152],"interaction":[153],"process":[154],"establish":[156],"image-text":[158],"Extensive":[161],"experiments":[162],"show":[163],"proposed":[166],"achieves":[168],"new":[169],"state-of-the-art":[170],"three":[173],"benchmark":[174],"datasets":[175],"also":[177],"performs":[178],"well":[179],"domain":[182],"generalization":[183],"task.":[184],"Our":[185],"code":[186],"is":[187],"available":[188],"at":[189],"https://github.com/y416f/FSRL.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}