{"id":"https://openalex.org/W7138112619","doi":"https://doi.org/10.1609/aaai.v40i14.38199","title":"KPDM: Key Phrase Dynamic Masking for Robust Text-to-Image Person Retrieval","display_name":"KPDM: Key Phrase Dynamic Masking for Robust Text-to-Image Person Retrieval","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138112619","doi":"https://doi.org/10.1609/aaai.v40i14.38199"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i14.38199","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38199","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38199/42161","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38199/42161","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101970691","display_name":"Sisi You","orcid":"https://orcid.org/0009-0004-2173-1694"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaofeng You","raw_affiliation_strings":["School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028744556","display_name":"Tianle Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianle Miao","raw_affiliation_strings":["School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723857","display_name":"Qihang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Chen","raw_affiliation_strings":["School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712184","display_name":"Xin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Intelligent Technology Co., Ltd of Chinese Construction Third Engineering Bureau"],"affiliations":[{"raw_affiliation_string":"Intelligent Technology Co., Ltd of Chinese Construction Third Engineering Bureau","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059836797","display_name":"Zhuo Cheng","orcid":"https://orcid.org/0000-0002-7003-7605"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Cheng","raw_affiliation_strings":["School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129674429","display_name":"Dapeng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Luo","raw_affiliation_strings":["School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Electronic Information, China University of Geosciences, Wuhan 430074, China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101970691"],"corresponding_institution_ids":["https://openalex.org/I3124059619"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41889881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"12099","last_page":"12107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5128999948501587,"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":0.5128999948501587,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.15029999613761902,"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":0.09560000151395798,"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/masking","display_name":"Masking (illustration)","score":0.7055000066757202},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6305999755859375},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6227999925613403},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.616100013256073},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.4772999882698059},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4569999873638153},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4431999921798706},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42890000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145999908447266},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6588000059127808},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4569999873638153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3303999900817871},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i14.38199","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38199","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38199/42161","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38199","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38199","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38199/42161","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"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/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/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/G8690242807","display_name":null,"funder_award_id":"62373338","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138112619.pdf","grobid_xml":"https://content.openalex.org/works/W7138112619.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"person":[1],"re-identification":[2],"(TIReID)":[3],"aims":[4],"to":[5,34,61,151,163,187],"retrieve":[6],"the":[7,43,53,65,79,85,93,97,128,192,208,212,227,233],"most":[8],"relevant":[9],"pedestrian":[10,76,166],"images":[11,77],"from":[12,68],"an":[13,69],"image":[14,70,167,172],"gallery":[15],"based":[16,118],"on":[17,64,119,207,226,232],"natural":[18],"language":[19,148],"descriptions.":[20],"Recent":[21],"studies":[22],"have":[23],"achieved":[24],"significant":[25],"performance":[26],"improvements":[27],"by":[28,134,215],"leveraging":[29],"Masked":[30],"Language":[31],"Modeling":[32],"(MLM)":[33],"align":[35],"fine-grained":[36,114,153],"information":[37,80],"through":[38],"local":[39,58,115,155],"matching.":[40],"However,":[41],"in":[42,75],"text":[44,49,132],"feature":[45,62,71],"extraction,":[46],"randomly":[47],"masking":[48,141],"tokens":[50,133],"may":[51,99],"disrupt":[52],"semantic":[54,129],"relationships":[55,130],"between":[56,131],"these":[57,108],"tokens,":[59],"leading":[60],"misalignment;":[63],"other":[66],"hand,":[67],"perspective,":[72],"redundant":[73,171],"patches":[74],"hinder":[78],"interaction":[81],"across":[82],"modalities.":[83],"Moreover,":[84],"presence":[86],"of":[87,224],"noisy":[88,189],"image-text":[89,184],"pairs":[90],"further":[91],"complicates":[92],"learning":[94],"process,":[95],"as":[96],"model":[98,193],"be":[100],"misled":[101],"into":[102],"recognizing":[103],"incorrect":[104],"patterns.":[105],"To":[106],"address":[107],"issues,":[109],"we":[110,126,158,175],"propose":[111,176],"a":[112,136,145,177],"robust":[113],"alignment":[116],"framework":[117],"Key":[120],"Phrase":[121],"Dynamic":[122],"Mask":[123],"(KPDM).":[124],"First,":[125],"strengthen":[127],"implementing":[135],"\"adjective":[137],"+":[138],"noun''":[139],"phrase-level":[140],"strategy,":[142],"and":[143,204,217,230],"design":[144],"frequency-based":[146],"masked":[147],"loss":[149],"(FMLM)":[150],"supervise":[152],"semantic-level":[154],"alignment.":[156],"Second,":[157],"integrate":[159],"cross-layer":[160],"importance":[161],"estimation":[162],"highlight":[164],"key":[165],"representations":[168],"while":[169],"removing":[170],"features.":[173],"Third,":[174],"trusted":[178],"consensus":[179],"partitioning":[180],"mechanism,":[181],"utilizing":[182],"intra-identity":[183],"similarity":[185],"distributions":[186],"identify":[188],"pairs,":[190],"enhancing":[191],"robustness.":[194],"Extensive":[195],"experiments":[196],"show":[197],"that":[198],"our":[199],"method":[200],"achieves":[201,221],"67.95%":[202],"Rank-1":[203,222],"51.88%":[205],"mAP":[206],"RSTPReid":[209],"dataset,":[210,235],"exceeding":[211],"previous":[213],"state-of-the-art":[214],"2.6%":[216],"1%.":[218],"Furthermore,":[219],"KPDM":[220],"accuracies":[223],"75.97%":[225],"CUHK-PEDES":[228],"dataset":[229],"67.78%":[231],"ICFG-PEDES":[234],"outperforming":[236],"earlier":[237],"methods.":[238]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}