{"id":"https://openalex.org/W4400233438","doi":"https://doi.org/10.1109/iscas58744.2024.10557902","title":"Audio-Visual Cross-Modal Generation with Multimodal Variational Generative Model","display_name":"Audio-Visual Cross-Modal Generation with Multimodal Variational Generative Model","publication_year":2024,"publication_date":"2024-05-19","ids":{"openalex":"https://openalex.org/W4400233438","doi":"https://doi.org/10.1109/iscas58744.2024.10557902"},"language":"en","primary_location":{"id":"doi:10.1109/iscas58744.2024.10557902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10557902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113274442","display_name":"Zhubin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086011","display_name":"China International Science and Technology Cooperation","ror":"https://ror.org/00bsdxt65","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210086011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhubin Xu","raw_affiliation_strings":["Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China","institution_ids":["https://openalex.org/I4210086011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075474564","display_name":"Tianlei Wang","orcid":"https://orcid.org/0000-0002-4498-4326"},"institutions":[{"id":"https://openalex.org/I4210086011","display_name":"China International Science and Technology Cooperation","ror":"https://ror.org/00bsdxt65","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210086011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlei Wang","raw_affiliation_strings":["Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China","institution_ids":["https://openalex.org/I4210086011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013971053","display_name":"Dekang Liu","orcid":"https://orcid.org/0000-0003-1630-5928"},"institutions":[{"id":"https://openalex.org/I4210086011","display_name":"China International Science and Technology Cooperation","ror":"https://ror.org/00bsdxt65","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210086011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dekang Liu","raw_affiliation_strings":["Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China","institution_ids":["https://openalex.org/I4210086011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078878760","display_name":"Dinghan Hu","orcid":"https://orcid.org/0000-0003-1493-0041"},"institutions":[{"id":"https://openalex.org/I4210086011","display_name":"China International Science and Technology Cooperation","ror":"https://ror.org/00bsdxt65","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210086011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dinghan Hu","raw_affiliation_strings":["Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China","institution_ids":["https://openalex.org/I4210086011"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035422552","display_name":"Huanqiang Zeng","orcid":"https://orcid.org/0000-0002-2802-7745"},"institutions":[{"id":"https://openalex.org/I119045251","display_name":"Huaqiao University","ror":"https://ror.org/03frdh605","country_code":"CN","type":"education","lineage":["https://openalex.org/I119045251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanqiang Zeng","raw_affiliation_strings":["Huaqiao University,School of Engineering and School of Information Science and Engineering,Fujian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huaqiao University,School of Engineering and School of Information Science and Engineering,Fujian,China","institution_ids":["https://openalex.org/I119045251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074063024","display_name":"Jiuwen Cao","orcid":"https://orcid.org/0000-0002-6480-5794"},"institutions":[{"id":"https://openalex.org/I4210086011","display_name":"China International Science and Technology Cooperation","ror":"https://ror.org/00bsdxt65","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210086011"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuwen Cao","raw_affiliation_strings":["Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning and I-Health International Cooperation Base of Zhejiang Province,Zhejiang,China","institution_ids":["https://openalex.org/I4210086011"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.934499979019165,"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/T11309","display_name":"Music and Audio Processing","score":0.934499979019165,"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":0.7247521281242371},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6965054869651794},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.677735447883606},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4593617618083954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43883827328681946},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4382564127445221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4249432682991028},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.340770959854126},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17021659016609192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247521281242371},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6965054869651794},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.677735447883606},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4593617618083954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43883827328681946},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4382564127445221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4249432682991028},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.340770959854126},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17021659016609192},{"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/iscas58744.2024.10557902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10557902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":34,"referenced_works":["https://openalex.org/W1539811621","https://openalex.org/W1959608418","https://openalex.org/W2112796928","https://openalex.org/W2556013083","https://openalex.org/W2587822999","https://openalex.org/W2759171953","https://openalex.org/W2784461021","https://openalex.org/W2786541991","https://openalex.org/W2797583228","https://openalex.org/W2936900244","https://openalex.org/W2962960500","https://openalex.org/W2963066677","https://openalex.org/W2963663420","https://openalex.org/W2987472543","https://openalex.org/W2990113535","https://openalex.org/W2995458432","https://openalex.org/W3101943858","https://openalex.org/W3176404283","https://openalex.org/W3203982370","https://openalex.org/W3215517185","https://openalex.org/W4221139382","https://openalex.org/W4289761690","https://openalex.org/W4312655926","https://openalex.org/W4320013936","https://openalex.org/W6640963894","https://openalex.org/W6687506355","https://openalex.org/W6730357551","https://openalex.org/W6748018729","https://openalex.org/W6748455135","https://openalex.org/W6750665317","https://openalex.org/W6752910514","https://openalex.org/W6767441326","https://openalex.org/W6771605003","https://openalex.org/W6779792965"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Audio":[0],"and":[1,38,47,165],"Visual":[2],"are":[3],"two":[4,161],"important":[5],"visual":[6,39],"modalities":[7,51,56],"in":[8,21,141],"video":[9],"content":[10],"understanding.":[11],"However,":[12],"the":[13,26,33,45,54,58,97,125,132,143,148],"absence":[14],"of":[15,78,99,106,128],"one":[16],"modality":[17,79],"may":[18],"be":[19,139],"observed":[20],"practical":[22],"applications":[23],"due":[24],"to":[25,32,52,74,110,123,138],"real":[27],"environmental":[28],"factors,":[29],"which":[30],"leads":[31],"information":[34,49],"loss.":[35,81],"Therefore,":[36],"audio":[37],"fusion":[40],"is":[41,72,85,121,136],"focused":[42],"on":[43,160],"using":[44,88],"shared":[46],"complementary":[48],"between":[50],"recover":[53],"missing":[55,100,129],"from":[57],"available":[59,107],"data":[60,80,102,144],"modalities.":[61,108,130],"In":[62],"this":[63,76],"paper,":[64],"an":[65],"Adversarial":[66],"Hierarchical":[67],"Variational":[68,91],"Auto-Encoder":[69],"(Adv-HVAE)":[70],"model":[71,94],"proposed":[73],"solve":[75],"problem":[77],"A":[82],"multimodal":[83,115],"representation":[84],"first":[86],"learned":[87],"a":[89,112,117],"hierarchical":[90],"Autoencoder":[92],"(VAE)":[93],"that":[95,154],"enables":[96],"generation":[98,119,158],"modal":[101],"under":[103],"any":[104],"subset":[105],"Also":[109],"obtain":[111],"more":[113],"robust":[114],"representation,":[116],"feature":[118],"network":[120,135],"utilized":[122],"approximate":[124],"latent":[126],"distribution":[127],"Finally,":[131],"adversarial":[133],"training":[134],"shown":[137],"effective":[140],"improving":[142],"quality":[145],"generated":[146],"through":[147],"Adv-HVAE":[149,155],"framework.":[150],"Experimental":[151],"results":[152,159],"demonstrate":[153],"achieves":[156],"best":[157],"benchmark":[162],"datasets,":[163],"avMNIST":[164],"Sub-URMP.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}