{"id":"https://openalex.org/W3154807520","doi":"https://doi.org/10.1007/s11633-021-1293-0","title":"Deep Audio-visual Learning: A Survey","display_name":"Deep Audio-visual Learning: A Survey","publication_year":2021,"publication_date":"2021-04-15","ids":{"openalex":"https://openalex.org/W3154807520","doi":"https://doi.org/10.1007/s11633-021-1293-0","mag":"3154807520"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-021-1293-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-021-1293-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-021-1293-0.pdf","source":{"id":"https://openalex.org/S28082686","display_name":"International Journal of Automation and Computing","issn_l":"1476-8186","issn":["1476-8186","1751-8520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Automation and Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-021-1293-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101589497","display_name":"Hao Zhu","orcid":"https://orcid.org/0000-0003-2155-1488"},"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"]},{"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/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":true,"raw_author_name":"Hao Zhu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064812067","display_name":"Mandi Luo","orcid":"https://orcid.org/0000-0001-8298-3220"},"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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man-Di Luo","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, 100049, China"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431257","display_name":"Rui Wang","orcid":"https://orcid.org/0009-0003-8935-3119"},"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"]},{"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/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":"Rui Wang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"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":"Ai-Hua Zheng","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China","Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, 100049, China"],"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC) and National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of the Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101589497"],"corresponding_institution_ids":["https://openalex.org/I143868143","https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":19.2915,"has_fulltext":true,"cited_by_count":161,"citation_normalized_percentile":{"value":0.99719233,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"18","issue":"3","first_page":"351","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.9057133793830872},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7199857831001282},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7139980792999268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865118741989136},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5964140892028809},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47296279668807983},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4558999240398407},{"id":"https://openalex.org/keywords/visual-learning","display_name":"Visual learning","score":0.45331692695617676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43555566668510437},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3514930009841919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34605708718299866},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33542484045028687},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.11967694759368896},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11476650834083557}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.9057133793830872},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7199857831001282},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7139980792999268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865118741989136},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5964140892028809},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47296279668807983},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4558999240398407},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.45331692695617676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43555566668510437},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3514930009841919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34605708718299866},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33542484045028687},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.11967694759368896},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11476650834083557},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11633-021-1293-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-021-1293-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-021-1293-0.pdf","source":{"id":"https://openalex.org/S28082686","display_name":"International Journal of Automation and Computing","issn_l":"1476-8186","issn":["1476-8186","1751-8520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Automation and Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11633-021-1293-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-021-1293-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-021-1293-0.pdf","source":{"id":"https://openalex.org/S28082686","display_name":"International Journal of Automation and Computing","issn_l":"1476-8186","issn":["1476-8186","1751-8520"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Automation and Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3254430106","display_name":null,"funder_award_id":"61976002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6051939103","display_name":null,"funder_award_id":"2016YFB1001001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8114646031","display_name":null,"funder_award_id":"2016Y","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3154807520.pdf","grobid_xml":"https://content.openalex.org/works/W3154807520.grobid-xml"},"referenced_works_count":191,"referenced_works":["https://openalex.org/W192383697","https://openalex.org/W653761051","https://openalex.org/W1482998036","https://openalex.org/W1526392145","https://openalex.org/W1603228541","https://openalex.org/W1632780230","https://openalex.org/W1797158261","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W1974932989","https://openalex.org/W1977985044","https://openalex.org/W2007201420","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2042533225","https://openalex.org/W2064675550","https://openalex.org/W2065274193","https://openalex.org/W2079735306","https://openalex.org/W2096391593","https://openalex.org/W2099471712","https://openalex.org/W2106277773","https://openalex.org/W2106488367","https://openalex.org/W2115096495","https://openalex.org/W2121486117","https://openalex.org/W2136155248","https://openalex.org/W2137823674","https://openalex.org/W2163922914","https://openalex.org/W2164899449","https://openalex.org/W2166318210","https://openalex.org/W2184188583","https://openalex.org/W2235381883","https://openalex.org/W2261706002","https://openalex.org/W2267805933","https://openalex.org/W2293741035","https://openalex.org/W2293856338","https://openalex.org/W2296073425","https://openalex.org/W2325939864","https://openalex.org/W2399733683","https://openalex.org/W2402172128","https://openalex.org/W2406846463","https://openalex.org/W2469134594","https://openalex.org/W2474638510","https://openalex.org/W2508023766","https://openalex.org/W2544224704","https://openalex.org/W2550980560","https://openalex.org/W2551572271","https://openalex.org/W2584032004","https://openalex.org/W2585824449","https://openalex.org/W2593116425","https://openalex.org/W2594690981","https://openalex.org/W2596164567","https://openalex.org/W2618799552","https://openalex.org/W2619697695","https://openalex.org/W2619947201","https://openalex.org/W2621109248","https://openalex.org/W2623327532","https://openalex.org/W2625027024","https://openalex.org/W2630245091","https://openalex.org/W2651884604","https://openalex.org/W2660943524","https://openalex.org/W2726515241","https://openalex.org/W2730531294","https://openalex.org/W2734984521","https://openalex.org/W2735663686","https://openalex.org/W2738406145","https://openalex.org/W2751873519","https://openalex.org/W2759171953","https://openalex.org/W2773686055","https://openalex.org/W2780124704","https://openalex.org/W2782422271","https://openalex.org/W2790649793","https://openalex.org/W2796292145","https://openalex.org/W2797090057","https://openalex.org/W2798453914","https://openalex.org/W2803193013","https://openalex.org/W2804600264","https://openalex.org/W2808631503","https://openalex.org/W2810311710","https://openalex.org/W2844030168","https://openalex.org/W2883222475","https://openalex.org/W2884460600","https://openalex.org/W2887051120","https://openalex.org/W2889380691","https://openalex.org/W2890952074","https://openalex.org/W2893436174","https://openalex.org/W2894931878","https://openalex.org/W2897492344","https://openalex.org/W2898871284","https://openalex.org/W2899129842","https://openalex.org/W2900292050","https://openalex.org/W2901694026","https://openalex.org/W2901907199","https://openalex.org/W2910165986","https://openalex.org/W2913302158","https://openalex.org/W2914217321","https://openalex.org/W2920377649","https://openalex.org/W2922538097","https://openalex.org/W2924355447","https://openalex.org/W2936229313","https://openalex.org/W2944294033","https://openalex.org/W2949117887","https://openalex.org/W2950388022","https://openalex.org/W2950864153","https://openalex.org/W2951237705","https://openalex.org/W2951270715","https://openalex.org/W2951611190","https://openalex.org/W2952186347","https://openalex.org/W2952350176","https://openalex.org/W2952746495","https://openalex.org/W2961193895","https://openalex.org/W2962715207","https://openalex.org/W2962732076","https://openalex.org/W2962770929","https://openalex.org/W2962843773","https://openalex.org/W2962865004","https://openalex.org/W2962879692","https://openalex.org/W2962907547","https://openalex.org/W2962960500","https://openalex.org/W2962968152","https://openalex.org/W2963019222","https://openalex.org/W2963047834","https://openalex.org/W2963066677","https://openalex.org/W2963081548","https://openalex.org/W2963115079","https://openalex.org/W2963192365","https://openalex.org/W2963218389","https://openalex.org/W2963290645","https://openalex.org/W2963460857","https://openalex.org/W2963528589","https://openalex.org/W2963663420","https://openalex.org/W2963680395","https://openalex.org/W2963775347","https://openalex.org/W2963801643","https://openalex.org/W2963807156","https://openalex.org/W2964048159","https://openalex.org/W2964109005","https://openalex.org/W2964207404","https://openalex.org/W2964245526","https://openalex.org/W2964345931","https://openalex.org/W2967735860","https://openalex.org/W2969490140","https://openalex.org/W2970404322","https://openalex.org/W2970903655","https://openalex.org/W2972526452","https://openalex.org/W2972728673","https://openalex.org/W2977809668","https://openalex.org/W2977816919","https://openalex.org/W2979157532","https://openalex.org/W2979894294","https://openalex.org/W2980581183","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2990113535","https://openalex.org/W2996906606","https://openalex.org/W2997685131","https://openalex.org/W3005359536","https://openalex.org/W3006974783","https://openalex.org/W3008809756","https://openalex.org/W3009754773","https://openalex.org/W3011424113","https://openalex.org/W3011519842","https://openalex.org/W3013436746","https://openalex.org/W3015215494","https://openalex.org/W3034211329","https://openalex.org/W3041053424","https://openalex.org/W3043066494","https://openalex.org/W3047985687","https://openalex.org/W3082970446","https://openalex.org/W3096780661","https://openalex.org/W3097741049","https://openalex.org/W3099284785","https://openalex.org/W3101943858","https://openalex.org/W3102619627","https://openalex.org/W3104797222","https://openalex.org/W3118548710","https://openalex.org/W3123318516","https://openalex.org/W3123798147","https://openalex.org/W3124972797","https://openalex.org/W3128999341","https://openalex.org/W4289665794","https://openalex.org/W6729540071","https://openalex.org/W6738806211","https://openalex.org/W6748181857","https://openalex.org/W6754337694","https://openalex.org/W6754392867","https://openalex.org/W6755694806","https://openalex.org/W6765307894","https://openalex.org/W6779669310","https://openalex.org/W6781075900","https://openalex.org/W6955071965","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Abstract":[0],"Audio-visual":[1],"learning,":[2,76],"aimed":[3],"at":[4],"exploiting":[5],"the":[6,34,61,88,100],"relationship":[7],"between":[8],"audio":[9],"and":[10,72,79,104],"visual":[11],"modalities,":[12],"has":[13],"drawn":[14],"considerable":[15],"attention":[16],"since":[17],"deep":[18],"learning":[19,57,64],"started":[20],"to":[21,27,32],"be":[22],"used":[23,102],"successfully.":[24],"Researchers":[25],"tend":[26],"leverage":[28],"these":[29],"two":[30],"modalities":[31],"improve":[33],"performance":[35],"of":[36,54,91],"previously":[37],"considered":[38],"single-modality":[39],"tasks":[40,65],"or":[41],"address":[42],"new":[43],"challenging":[44],"problems.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,98],"provide":[50],"a":[51],"comprehensive":[52],"survey":[53],"recent":[55],"audio-visual":[56,63,70,74,77,80],"development.":[58],"We":[59],"divide":[60],"current":[62],"into":[66],"four":[67],"different":[68],"subfields:":[69],"separation":[71],"localization,":[73],"correspondence":[75],"generation,":[78],"representation":[81],"learning.":[82],"State-of-the-art":[83],"methods,":[84],"as":[85,87],"well":[86],"remaining":[89],"challenges":[90],"each":[92],"subfield,":[93],"are":[94],"further":[95],"discussed.":[96],"Finally,":[97],"summarize":[99],"commonly":[101],"datasets":[103],"challenges.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}