{"id":"https://openalex.org/W4415707918","doi":"https://doi.org/10.1109/icme59968.2025.11209957","title":"Adapting Cross-Modal Semantic Discrepancy in Text-based Person Search","display_name":"Adapting Cross-Modal Semantic Discrepancy in Text-based Person Search","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707918","doi":"https://doi.org/10.1109/icme59968.2025.11209957"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5089592676","display_name":"Xinpan Yuan","orcid":"https://orcid.org/0000-0001-9509-0755"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinpan Yuan","raw_affiliation_strings":["Hunan University of Technology,College of Computer Science,Zhuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University of Technology,College of Computer Science,Zhuzhou,China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774072","display_name":"Jiabao Li","orcid":"https://orcid.org/0000-0003-3701-7677"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Li","raw_affiliation_strings":["Hunan University of Technology,College of Computer Science,Zhuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University of Technology,College of Computer Science,Zhuzhou,China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113812275","display_name":"Wei Xia","orcid":"https://orcid.org/0000-0002-6366-5080"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Hunan University of Technology,College of Computer Science,Zhuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University of Technology,College of Computer Science,Zhuzhou,China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111287755","display_name":"Wenguang Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Gan","raw_affiliation_strings":["Hunan University of Technology,College of Computer Science,Zhuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University of Technology,College of Computer Science,Zhuzhou,China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079500442","display_name":"Ying Ma","orcid":"https://orcid.org/0000-0003-2104-8751"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxi Ying","raw_affiliation_strings":["Hunan University of Technology,College of Computer Science,Zhuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University of Technology,College of Computer Science,Zhuzhou,China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038781609","display_name":"Liujie Hua","orcid":"https://orcid.org/0000-0002-2756-1540"},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujie Hua","raw_affiliation_strings":["Hunan University of Technology,College of Computer Science,Zhuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University of Technology,College of Computer Science,Zhuzhou,China","institution_ids":["https://openalex.org/I49934816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I49934816"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6858999729156494,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6858999729156494,"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":0.10209999978542328,"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":0.06729999929666519,"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/constraint","display_name":"Constraint (computer-aided design)","score":0.7506999969482422},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.49799999594688416},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38449999690055847},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.3837999999523163},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.3492000102996826}],"concepts":[{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7506999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3837999999523163},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311213","display_name":"Education Department of Hunan Province","ror":"https://ror.org/05ckg3w11"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2270070752","https://openalex.org/W2962784628","https://openalex.org/W2963047834","https://openalex.org/W2963449390","https://openalex.org/W2997421053","https://openalex.org/W3024059432","https://openalex.org/W3093206719","https://openalex.org/W3095440956","https://openalex.org/W3206868111","https://openalex.org/W4200633094","https://openalex.org/W4283818632","https://openalex.org/W4297821751","https://openalex.org/W4304087170","https://openalex.org/W4312359729","https://openalex.org/W4321488152","https://openalex.org/W4322730934","https://openalex.org/W4385764787","https://openalex.org/W4386065353","https://openalex.org/W4386065462","https://openalex.org/W4386758381","https://openalex.org/W4388145471","https://openalex.org/W4392930945","https://openalex.org/W4399377915","https://openalex.org/W4411245246"],"related_works":[],"abstract_inverted_index":{"Text-Based":[0],"Person":[1],"Search":[2],"(TBPS)":[3],"aims":[4],"to":[5,25,30,53,89,122,142],"retrieve":[6],"target":[7],"pedestrian":[8],"images":[9],"through":[10],"language":[11],"descriptions.":[12],"However,":[13],"the":[14,41,62,91,95,98,128,144,147],"visual":[15],"attributes":[16],"and":[17,73],"textual":[18],"descriptions":[19],"of":[20,94,146],"different":[21],"identities":[22],"(pedestrians)":[23],"tend":[24],"exhibit":[26],"considerable":[27],"similarity,":[28],"leading":[29],"Similar":[31],"Semantic":[32,44],"Interference":[33],"(SSI).":[34],"To":[35],"mitigate":[36],"this":[37],"issue,":[38],"we":[39,60,114],"propose":[40],"Adapting":[42],"Cross-Modal":[43],"Discrepancy":[45],"(ACMSD)":[46],"method,":[47],"employing":[48],"a":[49,110],"cross-modal":[50,131],"constraint":[51],"approach":[52],"alleviate":[54],"interference":[55],"in":[56],"model":[57],"training.":[58],"Specifically,":[59],"introduce":[61],"Consistent":[63],"Constraint":[64],"Alignment":[65,119],"(CCA)":[66],"strategy,":[67],"which":[68],"establishes":[69],"both":[70],"inter-modal":[71],"alignment":[72],"intra-modal":[74],"alignment,":[75],"along":[76],"with":[77],"an":[78,116],"Identity-Balanced":[79],"Distribution":[80],"(IBD)":[81],"loss.":[82],"This":[83],"paradigm":[84],"utilizes":[85],"Cyclic":[86],"Image-Text":[87],"Contrastive":[88],"regularize":[90],"spatial":[92],"distribution":[93],"modalities,":[96],"while":[97],"IBD":[99],"loss":[100],"implicitly":[101],"clusters":[102],"strong":[103],"positive":[104],"samples":[105],"by":[106],"using":[107],"identity":[108],"as":[109],"key":[111],"index.":[112],"Additionally,":[113],"incorporate":[115],"Attention-based":[117],"Implicit":[118],"(AIA)":[120],"module":[121],"enforce":[123],"modality-specific":[124],"embeddings,":[125],"thereby":[126],"strengthening":[127],"interaction":[129],"between":[130],"information.":[132],"Extensive":[133],"experiments":[134],"are":[135],"conducted":[136],"on":[137],"three":[138],"public":[139],"benchmark":[140],"datasets":[141],"evaluate":[143],"performance":[145],"ACMSD":[148],"method.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}