{"id":"https://openalex.org/W4395027807","doi":"https://doi.org/10.1109/tcsvt.2024.3392831","title":"Fine-Granularity Alignment for Text-Based Person Retrieval Via Semantics-Centric Visual Division","display_name":"Fine-Granularity Alignment for Text-Based Person Retrieval Via Semantics-Centric Visual Division","publication_year":2024,"publication_date":"2024-04-23","ids":{"openalex":"https://openalex.org/W4395027807","doi":"https://doi.org/10.1109/tcsvt.2024.3392831"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3392831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3392831","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","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/A5082709923","display_name":"Zhimin Wei","orcid":"https://orcid.org/0000-0001-9489-5199"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhimin Wei","raw_affiliation_strings":["School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042794725","display_name":"Z. Y. Zhang","orcid":"https://orcid.org/0000-0002-0607-8605"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Zhang","raw_affiliation_strings":["School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032693575","display_name":"Peng Wu","orcid":"https://orcid.org/0000-0003-2938-6798"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101464181","display_name":"Ji Wang","orcid":"https://orcid.org/0000-0001-7077-3402"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wang","raw_affiliation_strings":["School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396097","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-9218-9132"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082709923"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.6909,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91082437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"34","issue":"9","first_page":"8242","last_page":"8252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9955000281333923,"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":0.9955000281333923,"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":0.9896000027656555,"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":0.9728999733924866,"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":0.7855221629142761},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.7214889526367188},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6419643759727478},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.5786237120628357},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4927857220172882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46534737944602966},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36649274826049805},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3588970899581909},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18134090304374695},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.10324442386627197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09221199154853821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855221629142761},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7214889526367188},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6419643759727478},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.5786237120628357},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4927857220172882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46534737944602966},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36649274826049805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3588970899581909},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18134090304374695},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.10324442386627197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09221199154853821}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3392831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3392831","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G766136092","display_name":null,"funder_award_id":"2021JCW-03","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"},{"id":"https://openalex.org/G8813799148","display_name":null,"funder_award_id":"U23B2013","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/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2185175083","https://openalex.org/W2801814609","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2943911770","https://openalex.org/W2963047834","https://openalex.org/W2963383990","https://openalex.org/W2963449390","https://openalex.org/W2963882743","https://openalex.org/W2985951359","https://openalex.org/W2994983839","https://openalex.org/W2997421053","https://openalex.org/W3015686580","https://openalex.org/W3024059432","https://openalex.org/W3035539956","https://openalex.org/W3093025987","https://openalex.org/W3095440956","https://openalex.org/W3099614098","https://openalex.org/W3111255625","https://openalex.org/W3120182027","https://openalex.org/W3147954272","https://openalex.org/W3154169267","https://openalex.org/W3165835426","https://openalex.org/W3184033217","https://openalex.org/W3187261085","https://openalex.org/W3189221782","https://openalex.org/W3206868111","https://openalex.org/W4225159440","https://openalex.org/W4292945941","https://openalex.org/W4297833440","https://openalex.org/W4304087170","https://openalex.org/W4304098245","https://openalex.org/W4312310776","https://openalex.org/W4312998013","https://openalex.org/W4316660800","https://openalex.org/W4321231469","https://openalex.org/W4323714307","https://openalex.org/W4375928712","https://openalex.org/W4376607991","https://openalex.org/W4385245566","https://openalex.org/W4386758381","https://openalex.org/W4388145471","https://openalex.org/W4389318018","https://openalex.org/W4389920963","https://openalex.org/W6674238660","https://openalex.org/W6755207826","https://openalex.org/W6788774013","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798810632","https://openalex.org/W6802411921","https://openalex.org/W6811013733","https://openalex.org/W6842542540","https://openalex.org/W6850427756"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4382701072","https://openalex.org/W4256502920"],"abstract_inverted_index":{"Text-based":[0],"Person":[1],"Retrieval":[2],"aims":[3,128],"to":[4,88,129,153,159,170,183],"search":[5],"the":[6,26,54,71,135,160,172,175],"target":[7],"pedestrian":[8],"image":[9,16],"from":[10,134],"video":[11],"surveillance":[12],"or":[13,45],"a":[14,19,96,109,113,120,147,164],"large":[15],"database":[17],"with":[18,101],"text":[20],"description.":[21],"Previous":[22],"works":[23],"have":[24],"recognized":[25],"significance":[27],"of":[28,203,213],"mining":[29],"local":[30,50,155],"information":[31],"in":[32,201,223],"images":[33,64],"and":[34,36,65,80,119,163,216],"descriptions":[35],"performing":[37],"fine-grained":[38,131,186],"alignment.":[39],"These":[40],"approaches":[41],"adopt":[42],"hard":[43],"division":[44],"auxiliary":[46],"networks":[47],"for":[48,62,141],"locating":[49],"visual":[51,156],"regions.":[52],"However,":[53],"two":[55],"existing":[56],"ways":[57],"are":[58],"not":[59],"flexible":[60],"enough":[61],"various":[63],"may":[66],"even":[67],"bring":[68],"noise.":[69],"Meanwhile,":[70],"Vision-Language":[72],"Pre-training":[73],"models":[74],"like":[75],"CLIP":[76],"exhibit":[77],"strong":[78],"generalization":[79],"zero-shot":[81],"abilities,":[82],"which":[83,138],"provide":[84],"an":[85,210],"available":[86,222],"way":[87],"this":[89,92],"issue.":[90],"In":[91,143],"paper,":[93],"we":[94,145],"propose":[95,146],"novel":[97],"Fine-Granularity":[98],"Alignment":[99,123],"model":[100],"Semantics-Centric":[102],"Visual":[103,149],"Division":[104],"(SCVD).":[105],"Our":[106,219],"method":[107],"contains":[108],"Semantics":[110,166],"Deconstructor":[111],"(SD),":[112],"Cross-modal":[114],"Guided":[115],"Interaction":[116],"(CGI)":[117],"module,":[118],"Dynamic":[121],"Focus":[122],"(DFA)":[124],"module.":[125],"The":[126,178,188],"SD":[127],"extract":[130],"semantic":[132,161],"prompts":[133,162,173],"raw":[136],"description":[137],"is":[139,180,221],"easy-understand":[140],"CLIP.":[142],"CGI,":[144],"Text-Guided":[148],"Localization":[150],"(TVL)":[151],"module":[152,169],"generate":[154],"representations":[157],"according":[158],"Vision-Guided":[165],"Reconstruction":[167],"(VSR)":[168],"integrate":[171],"into":[174],"textual":[176],"representation.":[177],"DFA":[179],"used":[181],"finally":[182],"align":[184],"vision-text":[185],"information.":[187],"extensive":[189],"experiments":[190],"demonstrate":[191],"that":[192],"our":[193],"proposed":[194],"framework":[195],"significantly":[196],"outperforms":[197],"current":[198],"state-of-the-art":[199],"methods":[200],"terms":[202],"Rank@1":[204],"metric":[205],"on":[206],"three":[207],"benchmarks":[208],"by":[209],"absolute":[211],"gain":[212],"6.56%,":[214],"8.93%,":[215],"11.53%,":[217],"respectively.":[218],"code":[220],"https://github.com/tujun233/SCVD.git.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}