{"id":"https://openalex.org/W4402979205","doi":"https://doi.org/10.1109/icme57554.2024.10688134","title":"LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search","display_name":"LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979205","doi":"https://doi.org/10.1109/icme57554.2024.10688134"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100861568","display_name":"Yu Wu","orcid":"https://orcid.org/0009-0002-4233-6461"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007464615","display_name":"Haiguang Wang","orcid":"https://orcid.org/0000-0003-0796-725X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiguang Wang","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263078","display_name":"Mengxia Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxia Wu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346891","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-6628-0370"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101798820","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-2114-4674"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8367999792098999,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8367999792098999,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.8069999814033508,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7638000249862671,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7758862972259521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204581499099731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5379311442375183},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49257737398147583},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.486068993806839},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4187273383140564}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7758862972259521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204581499099731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379311442375183},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49257737398147583},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.486068993806839},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4187273383140564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5400000214576721,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2143017621","https://openalex.org/W2765793020","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2952122856","https://openalex.org/W2962858109","https://openalex.org/W2963341956","https://openalex.org/W2963449390","https://openalex.org/W3015686580","https://openalex.org/W3035524453","https://openalex.org/W3093025987","https://openalex.org/W3095440956","https://openalex.org/W3165835426","https://openalex.org/W3204887981","https://openalex.org/W3206868111","https://openalex.org/W4200633094","https://openalex.org/W4297821751","https://openalex.org/W4304098245","https://openalex.org/W4321231469","https://openalex.org/W4386065462","https://openalex.org/W4386158974","https://openalex.org/W4386758381","https://openalex.org/W4387968696","https://openalex.org/W4387969591","https://openalex.org/W4388145471","https://openalex.org/W4389331836","https://openalex.org/W4390190636","https://openalex.org/W4390874394"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W2916983164","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-based":[0],"person":[1,10],"search":[2],"aims":[3],"at":[4],"retrieving":[5],"images":[6,29],"of":[7,68,131,175],"a":[8,13,49,89],"particular":[9],"based":[11,83],"on":[12,84,145,165],"given":[14],"textual":[15],"description.":[16],"A":[17],"common":[18],"solution":[19],"for":[20,140],"this":[21],"task":[22],"is":[23],"to":[24,37],"directly":[25],"match":[26],"the":[27,69,100,123,129,132,149,154,166,173,176],"entire":[28,155],"and":[30,114,169],"texts,":[31],"i.e.,":[32],"global":[33],"alignment,":[34],"which":[35],"fails":[36],"deal":[38],"with":[39,88,108],"discerning":[40],"specific":[41],"details":[42],"that":[43],"discriminate":[44],"against":[45],"appearance-similar":[46],"people.":[47],"As":[48],"result,":[50],"some":[51],"works":[52],"shift":[53],"their":[54],"attention":[55,66,126],"towards":[56],"local":[57,77,111,141],"alignment.":[58,142],"One":[59],"group":[60],"matches":[61],"fine-grained":[62],"parts":[63,82],"using":[64],"forward":[65,125],"weights":[67],"transformer":[70,133],"yet":[71,87],"underutilizes":[72],"information.":[73],"Another":[74],"implicitly":[75],"conducts":[76],"alignment":[78,112],"by":[79,127],"reconstructing":[80],"masked":[81],"unmasked":[85],"context":[86],"biased":[90],"masking":[91,160],"strategy.":[92,161],"All":[93],"limit":[94],"performance":[95],"improvement.":[96],"This":[97],"paper":[98],"proposes":[99],"Local":[101],"Alignment":[102],"from":[103],"Image-Phrase":[104],"modeling":[105],"(LAIP)":[106],"framework,":[107],"Bidirectional":[109],"Attention-weighted":[110],"(BidirAtt)":[113],"Mask":[115],"Phrase":[116],"Modeling":[117],"(MPM)":[118],"module.":[119],"BidirAtt":[120],"goes":[121],"beyond":[122],"typical":[124],"considering":[128],"gradient":[130],"as":[134],"backward":[135],"attention,":[136],"utilizing":[137],"two-sided":[138],"information":[139],"MPM":[143],"focuses":[144],"mask":[146],"reconstruction":[147],"within":[148],"noun":[150],"phrase":[151],"rather":[152],"than":[153],"text,":[156],"ensuring":[157],"an":[158],"unbiased":[159],"Extensive":[162],"experiments":[163],"conducted":[164],"CUHK-PEDES,":[167],"ICFG-PEDES,":[168],"RSTPReid":[170],"datasets":[171],"demonstrate":[172],"superiority":[174],"LAIP":[177],"framework":[178],"over":[179],"existing":[180],"methods.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}