{"id":"https://openalex.org/W4223443319","doi":"https://doi.org/10.1109/tnnls.2022.3161314","title":"VAG: A Uniform Model for Cross-Modal Visual-Audio Mutual Generation","display_name":"VAG: A Uniform Model for Cross-Modal Visual-Audio Mutual Generation","publication_year":2022,"publication_date":"2022-04-08","ids":{"openalex":"https://openalex.org/W4223443319","doi":"https://doi.org/10.1109/tnnls.2022.3161314","pmid":"https://pubmed.ncbi.nlm.nih.gov/35394915"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3161314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3161314","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Wangli Hao","orcid":"https://orcid.org/0000-0001-7839-7261"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangli Hao","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7839-7261","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"He Guan","orcid":null},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Guan","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Center for Research on Intelligent Perception and Computing (CRIPAC), Institute of Automation, Chinese Academy of Sciences (CASIA), University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhaoxiang Zhang","orcid":"https://orcid.org/0000-0003-2648-3875"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxiang Zhang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing, Institute of Automation, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2648-3875","affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing, Institute of Automation, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":0.5857,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60146431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"36","issue":"3","first_page":"4196","last_page":"4208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.35499998927116394,"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":0.35499998927116394,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.2143000066280365,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1956000030040741,"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/audio-signal","display_name":"Audio signal","score":0.5792999863624573},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4966000020503998},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4961000084877014},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.48339998722076416},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47360000014305115},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41929998993873596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371000051498413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6212999820709229},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5792999863624573},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46860000491142273},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4442000091075897},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.37790000438690186},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.375},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C167940747","wikidata":"https://www.wikidata.org/wiki/Q63727227","display_name":"Audio signal flow","level":5,"score":0.26589998602867126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3161314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3161314","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35394915","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35394915","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3624945331","display_name":null,"funder_award_id":"62006231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4160143202","display_name":"\u7c7b\u8111\u795e\u7ecf\u7f51\u7edc\u5efa\u6a21\u3001\u5b66\u4e60\u4e0e\u5e94\u7528","funder_award_id":"61836014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5353429300","display_name":null,"funder_award_id":"U21B2042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7317538059","display_name":null,"funder_award_id":"62072457","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1970942930","https://openalex.org/W2026012689","https://openalex.org/W2285716245","https://openalex.org/W2504949052","https://openalex.org/W2759171953","https://openalex.org/W2895749211","https://openalex.org/W2918984654","https://openalex.org/W2944294033","https://openalex.org/W2962793481","https://openalex.org/W2963066677","https://openalex.org/W2963073614","https://openalex.org/W2963663420","https://openalex.org/W2963800363","https://openalex.org/W2964268978","https://openalex.org/W2976929305","https://openalex.org/W2981592093","https://openalex.org/W2991327923","https://openalex.org/W2996878574","https://openalex.org/W4293403276","https://openalex.org/W6621378261","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6685777725","https://openalex.org/W6713645886","https://openalex.org/W6718140377","https://openalex.org/W6730456101","https://openalex.org/W6741832134","https://openalex.org/W6753914649"],"related_works":[],"abstract_inverted_index":{"Considering":[0],"both":[1],"audio":[2,26,45,51,53],"and":[3,27,55,63,73,83],"visual":[4,47,49,56],"modalities":[5],"is":[6,29],"helpful":[7],"for":[8,25],"understanding":[9],"a":[10,30,35],"video.":[11],"In":[12],"the":[13,68,91,100,103],"face":[14],"of":[15,70,93,102],"harsh":[16],"environmental":[17],"interference":[18],"or":[19],"signal":[20,74],"packet":[21],"loss,":[22],"automatically":[23],"compensating":[24],"vision":[28],"challenging":[31],"task.":[32],"We":[33,79],"propose":[34],"dynamic":[36],"cross-modal":[37,85],"visual-audio":[38],"mutual":[39,87],"generation":[40,88],"model":[41],"(VAMG),":[42],"which":[43],"includes":[44],"to":[46,50,98],"conversion,":[48,52],"self-generation,":[54],"self-generation.":[57],"VAMG":[58],"jointly":[59],"optimizes":[60],"modal":[61],"reconstruction":[62],"adversarial":[64],"constraints,":[65],"effectively":[66],"solving":[67],"problems":[69],"structural":[71],"alignment":[72],"compensation":[75],"in":[76],"incomplete":[77],"videos.":[78],"conducted":[80],"an":[81],"instrument-oriented":[82],"pose-oriented":[84],"audio-visual":[86],"experiment":[89],"on":[90],"sub-University":[92],"Rochester":[94],"Musical":[95],"Performance":[96],"dataset":[97],"verify":[99],"effectiveness":[101],"model.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2022-04-14T00:00:00"}