{"id":"https://openalex.org/W4402979486","doi":"https://doi.org/10.1109/icme57554.2024.10687782","title":"Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios","display_name":"Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979486","doi":"https://doi.org/10.1109/icme57554.2024.10687782"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5038529708","display_name":"Ya Jiang","orcid":"https://orcid.org/0000-0003-1733-8887"},"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":"Ya Jiang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412670","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2410-2429"},"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,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101385418","display_name":"Maocheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maocheng Hu","raw_affiliation_strings":["National Intelligent Voice Innovation Center,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Intelligent Voice Innovation Center,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703619","display_name":"Pengfei Hu","orcid":"https://orcid.org/0000-0002-7935-886X"},"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":"Pengfei Hu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000077857","display_name":"Zeyan Liu","orcid":"https://orcid.org/0000-0001-9237-7603"},"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":"Zeyan Liu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060276344","display_name":"Shi Cheng","orcid":"https://orcid.org/0000-0002-7341-3135"},"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":"Shi Cheng","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005376611","display_name":"Zhaoxu Nian","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":"Zhaoxu Nian","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111099420","display_name":"Yuxuan Dong","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":"Yuxuan Dong","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105507458","display_name":"Mingqi Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingqi Cai","raw_affiliation_strings":["National Intelligent Voice Innovation Center,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Intelligent Voice Innovation Center,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046409305","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0002-8098-5625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]},{"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,Atlanta,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0572,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92532726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9937999844551086,"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":0.9937999844551086,"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":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9359999895095825,"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":0.6936983466148376},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6265304088592529},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6118997931480408},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5498420000076294},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5387609004974365},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.48139217495918274},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4142723083496094},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3960813879966736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3523954749107361},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3091159760951996},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24174648523330688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2369365096092224},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17443206906318665},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09011152386665344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936983466148376},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6265304088592529},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6118997931480408},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5498420000076294},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5387609004974365},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.48139217495918274},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4142723083496094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3960813879966736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3523954749107361},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3091159760951996},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24174648523330688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2369365096092224},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17443206906318665},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09011152386665344},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2114219351","https://openalex.org/W2123843894","https://openalex.org/W2292996718","https://openalex.org/W2746554716","https://openalex.org/W2810934215","https://openalex.org/W2916798096","https://openalex.org/W2918984654","https://openalex.org/W2936774411","https://openalex.org/W2964109005","https://openalex.org/W2969987364","https://openalex.org/W2997909293","https://openalex.org/W2998139081","https://openalex.org/W3011890046","https://openalex.org/W3081461453","https://openalex.org/W3083274258","https://openalex.org/W3110017807","https://openalex.org/W3163193264","https://openalex.org/W3197089327","https://openalex.org/W3206329344","https://openalex.org/W4312356258","https://openalex.org/W4312367758","https://openalex.org/W4324116353","https://openalex.org/W4372263497","https://openalex.org/W6631190155","https://openalex.org/W6684354967","https://openalex.org/W6745136726","https://openalex.org/W6853532597"],"related_works":["https://openalex.org/W3088112989","https://openalex.org/W2392793229","https://openalex.org/W2048373740","https://openalex.org/W2103761320","https://openalex.org/W2348824220","https://openalex.org/W3028432408","https://openalex.org/W2136123817","https://openalex.org/W2608696184","https://openalex.org/W2166350757","https://openalex.org/W2769041751"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"an":[3,46,64,87,108,117,124],"audio-visual":[4,82,125],"information":[5,26,44],"fusion":[6,83,90,96],"approach":[7],"to":[8,42,63,97,115,123,154],"sound":[9],"event":[10],"localization":[11],"and":[12,23,30,91,102,133,138],"detection":[13],"(SELD)":[14],"in":[15,148],"low-resource":[16],"scenarios.":[17],"We":[18],"aim":[19],"at":[20],"utilizing":[21],"audio":[22,56,101,118],"video":[24,103,110],"modality":[25],"through":[27],"cross-modal":[28,37],"learning":[29,39],"multi-modal":[31],"fusion.":[32],"First,":[33],"we":[34,78,106],"propose":[35,79],"a":[36,52,71,80,92,173],"teacher-student":[38],"(TSL)":[40],"framework":[41],"transfer":[43],"from":[45],"audio-only":[47],"teacher":[48],"model,":[49],"trained":[50,68],"on":[51,130],"rich":[53],"collection":[54],"of":[55,74,86,135,158],"data":[57,60,143],"with":[58,69],"multiple":[59],"augmentation":[61],"techniques,":[62],"audiovisual":[65],"student":[66],"model":[67,174],"only":[70],"limited":[72],"set":[73,144],"multimodal":[75],"data.":[76],"Next,":[77],"two-stage":[81],"strategy,":[84],"consisting":[85],"early":[88],"feature":[89],"late":[93],"video-guided":[94],"decision":[95],"exploit":[98],"synergies":[99],"between":[100],"modalities.":[104],"Finally,":[105],"introduce":[107],"innovative":[109],"pixel":[111],"swapping":[112,120],"(VPS)":[113],"technique":[114],"extend":[116],"channel":[119],"(ACS)":[121],"method":[122],"joint":[126],"augmentation.":[127],"Evaluation":[128],"results":[129],"the":[131,155,159,169],"Detection":[132],"Classification":[134],"Acoustic":[136],"Scenes":[137],"Events":[139],"(DCASE)":[140],"2023":[141,161],"Challenge":[142,162],"demonstrate":[145],"significant":[146],"improvements":[147],"SELD":[149,156],"performances.":[150],"Furthermore,":[151],"our":[152],"submission":[153],"task":[157],"DCASE":[160],"ranks":[163],"first":[164],"place":[165],"by":[166],"effectively":[167],"integrating":[168],"proposed":[170],"techniques":[171],"into":[172],"ensemble.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
