{"id":"https://openalex.org/W4394897075","doi":"https://doi.org/10.1109/tcsvt.2024.3390573","title":"Public-Private Attributes-Based Variational Adversarial Network for Audio-Visual Cross-Modal Matching","display_name":"Public-Private Attributes-Based Variational Adversarial Network for Audio-Visual Cross-Modal Matching","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4394897075","doi":"https://doi.org/10.1109/tcsvt.2024.3390573"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3390573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3390573","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/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":true,"raw_author_name":"Aihua Zheng","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832597","display_name":"Fan Yuan","orcid":"https://orcid.org/0009-0001-4071-3086"},"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":"Fan Yuan","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/A5114833544","display_name":"Haichuan Zhang","orcid":"https://orcid.org/0009-0005-0288-2937"},"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":"Haichuan Zhang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","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":false,"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/A5020274462","display_name":"Chao Tang","orcid":"https://orcid.org/0000-0002-8934-9537"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Hefei University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Hefei University, Hefei, China","institution_ids":["https://openalex.org/I39774598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"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":"Chenglong Li","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation and the Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017558628"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":1.0513,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73881904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"34","issue":"9","first_page":"8698","last_page":"8709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9871000051498413,"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":0.9871000051498413,"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/T11309","display_name":"Music and Audio Processing","score":0.9836999773979187,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9413999915122986,"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/adversarial-system","display_name":"Adversarial system","score":0.7564331293106079},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7131343483924866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6648421287536621},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5564395785331726},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5479341745376587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222219228744507},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46750032901763916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33123552799224854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23470202088356018},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2010803520679474},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08827587962150574}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7564331293106079},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7131343483924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648421287536621},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5564395785331726},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5479341745376587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222219228744507},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46750032901763916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33123552799224854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23470202088356018},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2010803520679474},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08827587962150574},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3390573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3390573","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/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/G849060900","display_name":null,"funder_award_id":"2208085J18","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1779483307","https://openalex.org/W1834627138","https://openalex.org/W1956343362","https://openalex.org/W2085662862","https://openalex.org/W2187089797","https://openalex.org/W2325939864","https://openalex.org/W2726515241","https://openalex.org/W2738069262","https://openalex.org/W2808260522","https://openalex.org/W2808631503","https://openalex.org/W2951237705","https://openalex.org/W2963026686","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2964055354","https://openalex.org/W2997819898","https://openalex.org/W2998315347","https://openalex.org/W3003383851","https://openalex.org/W3034725201","https://openalex.org/W3093411628","https://openalex.org/W3118548710","https://openalex.org/W3137758952","https://openalex.org/W3163658555","https://openalex.org/W3176579584","https://openalex.org/W3177326298","https://openalex.org/W3187885408","https://openalex.org/W3194247010","https://openalex.org/W3214311327","https://openalex.org/W4225776299","https://openalex.org/W4283382486","https://openalex.org/W4285170134","https://openalex.org/W4285207098","https://openalex.org/W4292262837","https://openalex.org/W4293568373","https://openalex.org/W4295035973","https://openalex.org/W4311415873","https://openalex.org/W4312886874","https://openalex.org/W4313007769","https://openalex.org/W4318811844","https://openalex.org/W4319777846","https://openalex.org/W4323644076","https://openalex.org/W4372341093","https://openalex.org/W4385810559","https://openalex.org/W4386071565","https://openalex.org/W4386076364","https://openalex.org/W4387885896","https://openalex.org/W6638116569","https://openalex.org/W6640850671","https://openalex.org/W6730998768","https://openalex.org/W6752791795","https://openalex.org/W6780248173","https://openalex.org/W6780593937"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Existing":[0],"audio-visual":[1,68,163],"cross-modal":[2,8,40,69,131,164],"matching":[3,29,165],"methods":[4],"focus":[5],"on":[6,162],"mitigating":[7],"heterogeneity":[9],"but":[10],"ignore":[11],"the":[12,18,28,61,87,95,102,115,124,149,167,170,175],"impact":[13],"of":[14,17,36,117,123,169],"intra-class":[15,37,103],"discrepancy":[16,38],"same":[19],"identity":[20],"in":[21,91,153],"different":[22],"scenarios,":[23],"which":[24,59,85],"might":[25],"greatly":[26],"limit":[27],"performance.":[30],"To":[31],"simultaneously":[32],"handle":[33],"both":[34],"problems":[35],"and":[39,64,119],"heterogeneity,":[41],"we":[42],"propose":[43],"a":[44,82,108],"novel":[45],"public-private":[46],"attributes-based":[47],"variational":[48,83],"adversarial":[49],"network":[50],"(":[51],"<italic":[52,73,135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[53,56,74,77,136,139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">P</i>":[54,75,137],"<sup":[55,76,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[57,78,140],"VANet),":[58],"captures":[60,86],"consistency":[62,116],"within":[63],"between":[65],"classes,":[66],"for":[67],"matching.":[70],"In":[71,133],"particular,":[72],"VANet":[79,141],"first":[80],"uses":[81],"auto-encoder,":[84],"inherent":[88,152],"global":[89],"information":[90,128],"diverse":[92],"scenarios":[93],"from":[94],"hidden":[96],"variable":[97],"through":[98],"reconstruction,":[99],"to":[100,113,129,147,156],"reduce":[101],"discrepancy.":[104],"Then":[105],"it":[106],"integrates":[107],"public":[109],"attributes":[110,144],"guidance":[111],"module":[112,146],"capture":[114],"audio":[118],"visual":[120],"by":[121],"supervision":[122],"common":[125],"high-level":[126],"semantic":[127],"mitigate":[130],"heterogeneity.":[132],"addition,":[134],"designs":[142],"private":[143],"embedding":[145],"enhance":[148],"discriminative":[150],"features":[151],"each":[154],"class":[155],"decrease":[157],"inter-class":[158],"similarity.":[159],"Extensive":[160],"experiments":[161],"demonstrate":[166],"effectiveness":[168],"proposed":[171],"approach":[172],"compared":[173],"with":[174],"state-of-the-art":[176],"methods.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
