{"id":"https://openalex.org/W4408697620","doi":"https://doi.org/10.1109/lsp.2025.3553424","title":"ViLNM: Visual-Language Noise Modeling for Text-to-Image Person Retrieval","display_name":"ViLNM: Visual-Language Noise Modeling for Text-to-Image Person Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408697620","doi":"https://doi.org/10.1109/lsp.2025.3553424"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3553424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3553424","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Guolin Xu","orcid":"https://orcid.org/0009-0003-5299-7797"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guolin Xu","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0003-5299-7797","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Feng","orcid":"https://orcid.org/0000-0002-8820-8388"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Feng","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-8820-8388","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102965312","display_name":"Yanying Chen","orcid":"https://orcid.org/0000-0001-7996-0677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanying Chen","raw_affiliation_strings":["CMA Key Open Laboratory of Transforming Climate Resources to Economy, Chongqing Institute of Meteorological Sciences, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMA Key Open Laboratory of Transforming Climate Resources to Economy, Chongqing Institute of Meteorological Sciences, Chongqing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guofan Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guofan Duan","raw_affiliation_strings":["Chongqing Metropolitan College of Science and Technology, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Metropolitan College of Science and Technology, Chongqing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102567029","display_name":"Mingliang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Zhou","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-1874-3641","affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72642636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"1386","last_page":"1390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9936000108718872,"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":0.9936000108718872,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9854999780654907,"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":0.9736999869346619,"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":0.7662750482559204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5528202652931213},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5264875888824463},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5158550143241882},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.465984046459198},{"id":"https://openalex.org/keywords/image-noise","display_name":"Image noise","score":0.4186001420021057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38552287220954895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33101627230644226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7662750482559204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5528202652931213},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5264875888824463},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5158550143241882},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.465984046459198},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.4186001420021057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38552287220954895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33101627230644226}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3553424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3553424","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3467323009","display_name":null,"funder_award_id":"62262006","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2883311563","https://openalex.org/W2894786240","https://openalex.org/W2896457183","https://openalex.org/W2963449390","https://openalex.org/W2998792609","https://openalex.org/W3189221782","https://openalex.org/W3204887981","https://openalex.org/W3206868111","https://openalex.org/W4304087170","https://openalex.org/W4321231469","https://openalex.org/W4385764787","https://openalex.org/W4386065462","https://openalex.org/W4387968696","https://openalex.org/W4388145471","https://openalex.org/W4390970441","https://openalex.org/W4392930945","https://openalex.org/W4393158793","https://openalex.org/W4402753821","https://openalex.org/W4402753981","https://openalex.org/W4408220440","https://openalex.org/W4408354259","https://openalex.org/W6740005241","https://openalex.org/W6747225742","https://openalex.org/W6767370287","https://openalex.org/W6788774013","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6798810632","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W1921169094","https://openalex.org/W366410996","https://openalex.org/W2183768935","https://openalex.org/W2004123705","https://openalex.org/W2793742470","https://openalex.org/W4239902399","https://openalex.org/W289407349","https://openalex.org/W2971191913","https://openalex.org/W946106684","https://openalex.org/W4379537582"],"abstract_inverted_index":{"Text-to-image":[0],"person":[1,9,52,129,153],"retrieval":[2],"(TPR)":[3],"focuses":[4],"on":[5,11,159],"finding":[6],"a":[7,57,70,88,114,133],"specific":[8],"based":[10],"the":[12,20,29,38,42,65,96,99,106,109,121,125,148],"textual":[13,100],"description,":[14],"and":[15,44,61,136,141,163],"most":[16],"methods":[17],"implicitly":[18],"assume":[19],"training":[21],"image-text":[22,30],"pairs":[23,31],"are":[24],"correctly":[25],"aligned.":[26],"In":[27],"practice,":[28],"exist":[32],"under-correlated":[33],"or":[34],"false-correlated":[35],"due":[36],"to":[37,56,112,119,146],"low":[39],"quality":[40],"of":[41,124],"images":[43],"annotation":[45],"errors.":[46],"Meanwhile,":[47],"remarkable":[48],"similarities":[49],"between":[50,59,151],"different":[51,128,152],"identities":[53],"may":[54],"lead":[55],"mismatch":[58],"text":[60],"image.":[62],"To":[63],"tackle":[64],"two":[66],"issues,":[67],"we":[68,86,131],"present":[69],"Visual-Language":[71],"Noise":[72,89],"Modeling":[73],"(ViLNM)":[74],"method":[75],"that":[76,94,102],"successfully":[77],"captures":[78],"robust":[79],"cross-modal":[80],"associations":[81],"even":[82],"with":[83],"noise.":[84],"Specifically,":[85],"design":[87],"Token":[90],"Aware":[91],"(NTA)":[92],"module":[93,145],"eliminates":[95],"words":[97,111],"in":[98],"description":[101],"do":[103],"not":[104],"match":[105],"image,":[107],"utilizing":[108],"matched":[110],"establish":[113],"more":[115],"reliable":[116],"association.":[117],"Besides,":[118],"enhance":[120],"recognition":[122],"ability":[123],"model":[126],"for":[127],"identities,":[130],"propose":[132],"Joint":[134],"Inter":[135],"Intra-Modal":[137],"Contrastive":[138],"Loss":[139],"(JII)":[140],"Local":[142],"Aggregation":[143],"(LA)":[144],"increase":[147],"feature":[149],"differences":[150],"identities.":[154],"We":[155],"conduct":[156],"comprehensive":[157],"experiments":[158],"three":[160],"public":[161],"benchmarks,":[162],"ViLNM":[164],"performs":[165],"best.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}