{"id":"https://openalex.org/W2974547267","doi":"https://doi.org/10.1109/dicta47822.2019.8945863","title":"Deep Latent Space Learning for Cross-Modal Mapping of Audio and Visual Signals","display_name":"Deep Latent Space Learning for Cross-Modal Mapping of Audio and Visual Signals","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2974547267","doi":"https://doi.org/10.1109/dicta47822.2019.8945863","mag":"2974547267"},"language":"en","primary_location":{"id":"doi:10.1109/dicta47822.2019.8945863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta47822.2019.8945863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.08685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016485532","display_name":"Shah Nawaz","orcid":"https://orcid.org/0000-0002-7715-4409"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Shah Nawaz","raw_affiliation_strings":["Department of Theoretical and Applied Science, University of Insubria, Varese, Italy","University of Insubria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Science, University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"University of Insubria","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003149553","display_name":"Muhammad Kamran Janjua","orcid":"https://orcid.org/0000-0002-5666-1700"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["IT","PK"],"is_corresponding":false,"raw_author_name":"Muhammad Kamran Janjua","raw_affiliation_strings":["SEECS, National University of Sciences and Technology, Islamabad, Pakistan","University of Insubria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SEECS, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]},{"raw_affiliation_string":"University of Insubria","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054778549","display_name":"Ignazio Gallo","orcid":"https://orcid.org/0000-0002-7076-8328"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ignazio Gallo","raw_affiliation_strings":["Department of Theoretical and Applied Science, University of Insubria, Varese, Italy","University of Insubria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Science, University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"University of Insubria","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061017734","display_name":"Arif Mahmood","orcid":"https://orcid.org/0000-0001-5986-9876"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Arif Mahmood","raw_affiliation_strings":["Department of Computer Science, Information Technology University, Lahore, Pakistan","Department of Computer Science Information Technology University  Lahore Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Information Technology University, Lahore, Pakistan","institution_ids":["https://openalex.org/I1323252656"]},{"raw_affiliation_string":"Department of Computer Science Information Technology University  Lahore Pakistan","institution_ids":["https://openalex.org/I1323252656"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087859719","display_name":"Alessandro Calefati","orcid":"https://orcid.org/0000-0003-3860-4785"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]},{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["IT","PK"],"is_corresponding":false,"raw_author_name":"Alessandro Calefati","raw_affiliation_strings":["Department of Theoretical and Applied Science, University of Insubria, Varese, Italy","[Information Technology University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Science, University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]},{"raw_affiliation_string":"[Information Technology University]","institution_ids":["https://openalex.org/I1323252656"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.996999979019165,"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/modal","display_name":"Modal","score":0.8114879131317139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766169309616089},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6309285759925842},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6073256731033325},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5982922315597534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5453996658325195},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4823188781738281},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47068458795547485},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44458597898483276},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4318099617958069},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43138253688812256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36818915605545044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34895771741867065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3400897979736328},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0775720477104187}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8114879131317139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766169309616089},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6309285759925842},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6073256731033325},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5982922315597534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5453996658325195},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4823188781738281},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47068458795547485},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44458597898483276},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4318099617958069},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43138253688812256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36818915605545044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34895771741867065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3400897979736328},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0775720477104187},{"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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/dicta47822.2019.8945863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta47822.2019.8945863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.08685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.08685","pdf_url":"https://arxiv.org/pdf/1909.08685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:irinsubria.uninsubria.it:11383/2083819","is_oa":false,"landing_page_url":"http://hdl.handle.net/11383/2083819","pdf_url":null,"source":{"id":"https://openalex.org/S4377196351","display_name":"IrInSubria (University of Insubria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115752224","host_organization_name":"University of Insubria","host_organization_lineage":["https://openalex.org/I115752224"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1909.08685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.08685","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2974547267","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.08685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.08685","pdf_url":"https://arxiv.org/pdf/1909.08685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2974547267.pdf","grobid_xml":"https://content.openalex.org/works/W2974547267.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W208009482","https://openalex.org/W1875842236","https://openalex.org/W1933349210","https://openalex.org/W2015394094","https://openalex.org/W2065428732","https://openalex.org/W2066078528","https://openalex.org/W2067140085","https://openalex.org/W2123024445","https://openalex.org/W2125436662","https://openalex.org/W2127211243","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2166563626","https://openalex.org/W2325939864","https://openalex.org/W2515770085","https://openalex.org/W2520774990","https://openalex.org/W2546190447","https://openalex.org/W2619697695","https://openalex.org/W2726515241","https://openalex.org/W2734984521","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2883222475","https://openalex.org/W2950761309","https://openalex.org/W2962756039","https://openalex.org/W2962918445","https://openalex.org/W2963480192","https://openalex.org/W2963801643","https://openalex.org/W2963887950","https://openalex.org/W2963899908","https://openalex.org/W2964109005","https://openalex.org/W2964121744","https://openalex.org/W3005368757","https://openalex.org/W6631190155","https://openalex.org/W6678470764","https://openalex.org/W6685183736","https://openalex.org/W6700903540","https://openalex.org/W6726453277","https://openalex.org/W6726946684","https://openalex.org/W6729831399","https://openalex.org/W6751966083","https://openalex.org/W6752791795","https://openalex.org/W6753468187"],"related_works":["https://openalex.org/W2997819898","https://openalex.org/W3009045332","https://openalex.org/W2773276919","https://openalex.org/W3161507032","https://openalex.org/W3171345413","https://openalex.org/W3214261769","https://openalex.org/W2963750245","https://openalex.org/W3092800257","https://openalex.org/W3019162146","https://openalex.org/W3118593445","https://openalex.org/W3197177945","https://openalex.org/W2982205216","https://openalex.org/W3209386620","https://openalex.org/W2896229655","https://openalex.org/W2971870814","https://openalex.org/W2949296282","https://openalex.org/W3038597925","https://openalex.org/W3101265641","https://openalex.org/W2887522866","https://openalex.org/W3177418244"],"abstract_inverted_index":{"We":[0,64],"propose":[1],"a":[2,18,25,31,74],"novel":[3,26],"deep":[4,33],"training":[5],"algorithm":[6],"for":[7,116],"joint":[8],"representation":[9,36],"of":[10,17,37,59,80,113],"audio":[11],"and":[12,66,87,97],"visual":[13],"information":[14],"which":[15,53],"consists":[16],"single":[19],"stream":[20],"network":[21],"(SSNet)":[22],"coupled":[23],"with":[24],"loss":[27],"function":[28],"to":[29,55],"learn":[30],"shared":[32,45],"latent":[34,46],"space":[35,47],"multimodal":[38],"information.":[39],"The":[40],"proposed":[41,70],"framework":[42],"characterizes":[43],"the":[44,50,57,69,105,111,114],"by":[48],"leveraging":[49],"class":[51],"centers":[52],"helps":[54],"eliminate":[56],"need":[58],"pairwise":[60],"or":[61],"triplet":[62],"supervision.":[63],"quantitatively":[65],"qualitatively":[67],"evaluate":[68],"approach":[71],"on":[72,78,94,104],"VoxCeleb,":[73],"benchmarks":[75],"audio-visual":[76],"dataset":[77],"multitude":[79],"tasks":[81],"including":[82],"cross-modal":[83,85,88,95,117],"verification,":[84],"matching":[86,98],"retrieval.":[89],"State-of-the-art":[90],"performance":[91],"is":[92],"achieved":[93],"verification":[96],"while":[99],"comparable":[100],"results":[101],"are":[102],"observed":[103],"remaining":[106],"applications.":[107,119],"Our":[108],"experiments":[109],"demonstrate":[110],"effectiveness":[112],"technique":[115],"biometric":[118]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}