{"id":"https://openalex.org/W4319586559","doi":"https://doi.org/10.1109/iscslp57327.2022.10038206","title":"A Study on Joint Modeling and Data Augmentation of Multi-Modalities for Audio-Visual Scene Classification","display_name":"A Study on Joint Modeling and Data Augmentation of Multi-Modalities for Audio-Visual Scene Classification","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586559","doi":"https://doi.org/10.1109/iscslp57327.2022.10038206"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038206","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-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/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China,NELSLIP,Hefei,China","NELSLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,NELSLIP,Hefei,China","NELSLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005930092","display_name":"Siyuan Zheng","orcid":"https://orcid.org/0000-0002-1031-9424"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Zheng","raw_affiliation_strings":["University of Science and Technology of China,NELSLIP,Hefei,China","NELSLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656670","display_name":"Yunqing Li","orcid":"https://orcid.org/0000-0003-4460-9400"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqing Li","raw_affiliation_strings":["University of Science and Technology of China,NELSLIP,Hefei,China","NELSLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078239339","display_name":"Yajian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajian Wang","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent Corporation,China","University of Science and Technology of China,NELSLIP,Hefei,China","NELSLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NELSLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113876348","display_name":"Yuzhong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yuzhong Wu","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent Corporation,China","Tencent Ethereal Audio Lab, Tencent Corporation, China","DSP & Speech Technology Laboratory, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"DSP & Speech Technology Laboratory, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079582557","display_name":"Hu Hu","orcid":"https://orcid.org/0000-0003-2101-8317"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu Hu","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","Computer Engineering School, University of Enna Kore, Italy"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Computer Engineering School, University of Enna Kore, Italy","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Tencent Ethereal Audio Lab, Tencent Corporation,China","University of Science and Technology of China,NELSLIP,Hefei,China","Tencent Ethereal Audio Lab, Tencent Corporation, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"University of Science and Technology of China,NELSLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100434900"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62720403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9847999811172485,"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/computer-science","display_name":"Computer science","score":0.8500908613204956},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6971111297607422},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6756854057312012},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6710879802703857},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6104217171669006},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.607446014881134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.584208607673645},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5148314833641052},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.49050015211105347},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47075918316841125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.436431348323822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4250660836696625},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42373210191726685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4124159812927246},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36473891139030457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32874661684036255},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21874889731407166},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21346762776374817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500908613204956},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6971111297607422},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6756854057312012},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6710879802703857},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6104217171669006},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.607446014881134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.584208607673645},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5148314833641052},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.49050015211105347},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47075918316841125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.436431348323822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4250660836696625},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42373210191726685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4124159812927246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36473891139030457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32874661684036255},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21874889731407166},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21346762776374817},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038206","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/649273","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/649273","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1555767263","https://openalex.org/W1686810756","https://openalex.org/W1880213544","https://openalex.org/W2017814585","https://openalex.org/W2077395415","https://openalex.org/W2108598243","https://openalex.org/W2113507809","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2528286866","https://openalex.org/W2593116425","https://openalex.org/W2732026016","https://openalex.org/W2936774411","https://openalex.org/W2963446712","https://openalex.org/W2969689033","https://openalex.org/W3035682985","https://openalex.org/W3097327166","https://openalex.org/W3100892511","https://openalex.org/W3106334569","https://openalex.org/W3161541317","https://openalex.org/W4293858004","https://openalex.org/W4295723153","https://openalex.org/W4298091485","https://openalex.org/W4307823382","https://openalex.org/W6637373629","https://openalex.org/W6727629558","https://openalex.org/W6747331233","https://openalex.org/W6752516136","https://openalex.org/W6779341498","https://openalex.org/W6885196408"],"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":{"In":[0],"this":[1],"paper,":[2],"we":[3,41],"propose":[4],"two":[5],"techniques,":[6],"namely":[7],"joint":[8,55,92],"modeling":[9,56],"and":[10,62],"data":[11,30,66],"augmentation,":[12],"to":[13,32,43,57,71,97,130],"improve":[14,99],"system":[15,116],"performances":[16],"for":[17,37,54],"audio-visual":[18,73],"scene":[19],"classification":[20],"(AVSC).":[21],"We":[22,48],"employ":[23],"pretrained":[24],"networks":[25],"trained":[26],"only":[27],"on":[28,103],"image":[29],"sets":[31],"extract":[33],"video":[34,61,79],"embedding;":[35],"whereas":[36],"audio":[38,63],"embedding":[39],"models,":[40],"decide":[42],"train":[44],"them":[45],"from":[46],"scratch.":[47],"explore":[49],"different":[50],"neural":[51],"network":[52],"architectures":[53],"effectively":[58],"combine":[59],"the":[60,78,81,104,119],"modalities.":[64],"Moreover,":[65],"augmentation":[67],"strategies":[68],"are":[69],"investigated":[70],"increase":[72],"training":[74],"set":[75,106],"size.":[76],"For":[77],"modality":[80],"effectiveness":[82],"of":[83,107,122],"several":[84],"operations":[85],"in":[86],"RandAugment":[87],"is":[88,95],"verified.":[89],"An":[90],"audio-video":[91],"mixup":[93],"scheme":[94],"proposed":[96],"further":[98],"AVSC":[100,127],"performances.":[101],"Evaluated":[102],"development":[105],"TAU":[108],"Urban":[109],"Audio":[110],"Visual":[111],"Scenes":[112],"2021,":[113],"our":[114],"final":[115],"can":[117],"achieve":[118],"best":[120],"accuracy":[121],"94.2%":[123],"among":[124],"all":[125],"single":[126],"systems":[128],"submitted":[129],"DCASE":[131],"2021":[132],"Task":[133],"1b.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-07T13:37:22.277990","created_date":"2025-10-10T00:00:00"}
