{"id":"https://openalex.org/W4394805464","doi":"https://doi.org/10.1109/tifs.2024.3388949","title":"Attribute-Guided Cross-Modal Interaction and Enhancement for Audio-Visual Matching","display_name":"Attribute-Guided Cross-Modal Interaction and Enhancement for Audio-Visual Matching","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394805464","doi":"https://doi.org/10.1109/tifs.2024.3388949"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2024.3388949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3388949","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"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 Information Forensics and Security","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/A5100784264","display_name":"Jiaxiang Wang","orcid":"https://orcid.org/0000-0003-3059-798X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxiang Wang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017558628","display_name":"Aihua Zheng","orcid":"https://orcid.org/0000-0002-9820-4743"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aihua Zheng","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China","the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"the Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395059","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-3674-7160"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112749024","display_name":"Ran He","orcid":"https://orcid.org/0000-0002-3807-991X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","Center for Research on Intelligent Perception and Computing, Institute of Automation, National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, Institute of Automation, National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030720334","display_name":"Jin Tang","orcid":"https://orcid.org/0000-0001-8375-3590"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Tang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100784264"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":3.1539,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92365643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":null,"first_page":"4986","last_page":"4998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9958000183105469,"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.853959321975708},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6150223612785339},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5645943880081177},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5632402300834656},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5615724325180054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5585584044456482},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4618832468986511},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4596227705478668},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45473912358283997},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.446095734834671},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2302311658859253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853959321975708},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6150223612785339},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5645943880081177},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5632402300834656},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5615724325180054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5585584044456482},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4618832468986511},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4596227705478668},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45473912358283997},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.446095734834671},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2302311658859253},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2024.3388949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3388949","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"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 Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4306577167","display_name":null,"funder_award_id":"62372003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G569029087","display_name":null,"funder_award_id":"2308085Y40","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G8442675014","display_name":null,"funder_award_id":"U20A20223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8709529125","display_name":null,"funder_award_id":"U21B2045","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/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1781854261","https://openalex.org/W2019111214","https://openalex.org/W2066078528","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2227324914","https://openalex.org/W2325939864","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2808260522","https://openalex.org/W2884366600","https://openalex.org/W2963066927","https://openalex.org/W2963137102","https://openalex.org/W2963225012","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964216321","https://openalex.org/W2974062151","https://openalex.org/W2997819898","https://openalex.org/W2997909293","https://openalex.org/W3007833402","https://openalex.org/W3017098848","https://openalex.org/W3024840775","https://openalex.org/W3034725201","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3048939150","https://openalex.org/W3093411628","https://openalex.org/W3099638501","https://openalex.org/W3104090442","https://openalex.org/W3118548710","https://openalex.org/W3154848313","https://openalex.org/W3165405144","https://openalex.org/W3177326298","https://openalex.org/W3182657421","https://openalex.org/W3186351311","https://openalex.org/W3189969088","https://openalex.org/W3200643978","https://openalex.org/W3208722310","https://openalex.org/W3214311327","https://openalex.org/W4211154280","https://openalex.org/W4221139382","https://openalex.org/W4224924564","https://openalex.org/W4285603046","https://openalex.org/W4286910290","https://openalex.org/W4292958273","https://openalex.org/W4304080363","https://openalex.org/W4312337341","https://openalex.org/W4312626422","https://openalex.org/W4312761738","https://openalex.org/W4312763854","https://openalex.org/W4312886874","https://openalex.org/W4312977351","https://openalex.org/W4313387422","https://openalex.org/W4313467239","https://openalex.org/W4318811844","https://openalex.org/W4372341093","https://openalex.org/W4385245566","https://openalex.org/W4386065847","https://openalex.org/W4386172447","https://openalex.org/W6631190155","https://openalex.org/W6752791795","https://openalex.org/W6772157574","https://openalex.org/W6798805250","https://openalex.org/W6800772757","https://openalex.org/W6802517928","https://openalex.org/W6802648153","https://openalex.org/W6841484515","https://openalex.org/W6851136385"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Audio-visual":[0],"matching":[1],"is":[2],"an":[3,161],"essential":[4],"task":[5],"that":[6],"measures":[7],"the":[8,22,42,80,94,100,125,137,168,174,207,210],"correlation":[9],"between":[10,185],"audio":[11,29],"clips":[12,30],"and":[13,31,47,70,99,128,140,149,180,217],"visual":[14],"images.":[15],"However,":[16],"current":[17],"methods":[18],"rely":[19],"solely":[20],"on":[21,201],"joint":[23],"embedding":[24],"of":[25,44,49,82,178,209],"global":[26,109],"features":[27,123,132,139,142,158,177],"from":[28],"face":[32],"image":[33],"pairs":[34],"to":[35,78,113,145],"learn":[36],"semantic":[37],"correlations.":[38],"This":[39],"approach":[40],"overlooks":[41],"importance":[43],"high-confidence":[45],"correlations":[46],"discrepancies":[48],"local":[50,85,116],"subtle":[51,86,156],"features,":[52,188],"which":[53,74,119],"are":[54,143,219],"crucial":[55],"for":[56,124,133],"cross-modal":[57,115,121,130],"matching.":[58],"To":[59,182],"address":[60],"this":[61],"issue,":[62],"we":[63,189],"propose":[64],"a":[65,191,196,202],"novel":[66,92],"Attribute-guided":[67,95,101],"Cross-modal":[68],"Interaction":[69,96],"Enhancement":[71,102],"Network":[72],"(ACIENet),":[73],"employs":[75,108],"multiple":[76,186],"attributes":[77],"explore":[79],"associations":[81],"different":[83,134,214],"key":[84],"features.":[87],"The":[88,105,152],"ACIENet":[89,211],"contains":[90],"two":[91],"modules:":[93],"(AGI)":[97],"module":[98,107,154],"(AGE)":[103],"module.":[104],"AGI":[106],"feature":[110,117],"alignment":[111],"similarity":[112],"guide":[114],"interactions,":[118],"enhances":[120],"association":[122],"same":[126],"identity":[127],"expands":[129],"distinctive":[131],"identities.":[135],"Additionally,":[136],"interactive":[138],"original":[141],"fused":[144],"ensure":[146],"intra-class":[147],"discriminability":[148],"inter-class":[150],"correspondence.":[151],"AGE":[153],"captures":[155],"attribute-related":[157,176],"by":[159],"using":[160],"attribute-driven":[162],"network,":[163],"thereby":[164],"enhancing":[165],"discrimination":[166],"at":[167,221],"attribute":[169,187],"level.":[170],"Specifically,":[171],"it":[172],"strengthens":[173],"combined":[175],"gender":[179],"nationality.":[181],"prevent":[183],"interference":[184],"design":[190],"multi-attribute":[192],"learning":[193],"network":[194],"as":[195],"parallel":[197],"framework.":[198],"Experiments":[199],"conducted":[200],"public":[203],"benchmark":[204],"dataset":[205],"demonstrate":[206],"efficacy":[208],"method":[212],"in":[213],"scenarios.":[215],"Code":[216],"models":[218],"available":[220],"https://github.com/w1018979952/ACIENet.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}