{"id":"https://openalex.org/W4408352510","doi":"https://doi.org/10.1109/icassp49660.2025.10888921","title":"MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation","display_name":"MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352510","doi":"https://doi.org/10.1109/icassp49660.2025.10888921"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102560553","display_name":"Hengyi Hong","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":"Hengyi Hong","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/A5090366902","display_name":"Ruoyu Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruoyu Wei","raw_affiliation_strings":["IFlytek Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Research,Hefei,China","institution_ids":[]}]},{"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":["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/A5101716884","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0003-4796-9444"},"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":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2561,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93548224,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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":0.9718999862670898,"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":0.738113284111023},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5818417072296143},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.538966178894043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521941602230072},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5053055882453918},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.47403717041015625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45353153347969055},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.41620147228240967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38604485988616943},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1526455283164978},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09533262252807617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738113284111023},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5818417072296143},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.538966178894043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521941602230072},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5053055882453918},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.47403717041015625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45353153347969055},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.41620147228240967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38604485988616943},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1526455283164978},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09533262252807617},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2964109005","https://openalex.org/W3005741390","https://openalex.org/W3083274258","https://openalex.org/W3097777922","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3206329344","https://openalex.org/W3210404408","https://openalex.org/W3214311327","https://openalex.org/W4312356258","https://openalex.org/W4312909419","https://openalex.org/W4324116353","https://openalex.org/W4372263497","https://openalex.org/W4375868779","https://openalex.org/W4390096820","https://openalex.org/W4392904168","https://openalex.org/W4392904420","https://openalex.org/W4393241166","https://openalex.org/W4402979486","https://openalex.org/W4404577061","https://openalex.org/W6631190155","https://openalex.org/W6779923105","https://openalex.org/W6853532597","https://openalex.org/W6860955266","https://openalex.org/W6874690668"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2329386257","https://openalex.org/W2503350049","https://openalex.org/W2909888262","https://openalex.org/W2397616145","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2397320258","https://openalex.org/W2056769785"],"abstract_inverted_index":{"Sound":[0],"event":[1],"localization":[2],"and":[3,18,101,106,120],"detection":[4],"with":[5,77],"source":[6,93],"distance":[7,78,94],"estimation":[8,95],"(3D":[9],"SELD)":[10],"involves":[11],"not":[12],"only":[13],"identifying":[14],"the":[15,25,34,59,75,84,90,99,126,131,139,145,151,157],"sound":[16,35,63,80],"category":[17],"its":[19],"direction-of-arrival":[20],"(DOA)":[21],"but":[22],"also":[23,112],"predicting":[24],"source's":[26],"distance,":[27],"aiming":[28],"to":[29,56,88],"provide":[30],"full":[31],"information":[32,61],"about":[33],"position.":[36],"This":[37],"paper":[38],"proposes":[39],"a":[40,69,114],"multi-stage":[41],"video":[42],"attention":[43],"network":[44],"(MVANet)":[45],"for":[46],"audio-visual":[47],"(AV)":[48],"3D":[49,153],"SELD.":[50],"Multi-stage":[51],"audio":[52],"features":[53],"are":[54,165],"used":[55,149],"adaptively":[57],"capture":[58],"spatial":[60],"of":[62,79,103,116,133,156],"sources":[64,81],"in":[65,98,150],"videos.":[66],"We":[67,111],"propose":[68],"novel":[70],"output":[71],"representation":[72],"that":[73],"combines":[74],"DOA":[76],"by":[82],"calculating":[83],"real":[85],"Cartesian":[86],"coordinates":[87],"address":[89],"newly":[91],"introduced":[92],"(SDE)":[96],"task":[97,155],"Detection":[100],"Classification":[102],"Acoustic":[104],"Scenes":[105],"Events":[107],"(DCASE)":[108],"2024":[109,159],"Challenge.":[110],"employ":[113],"variety":[115],"effective":[117],"data":[118],"augmentation":[119],"pre-training":[121],"methods.":[122],"Experimental":[123],"results":[124],"on":[125],"STARSS23":[127],"dataset":[128],"have":[129],"proven":[130],"effectiveness":[132],"our":[134,142],"proposed":[135],"MVANet.":[136],"By":[137],"integrating":[138],"aforementioned":[140],"techniques,":[141],"system":[143],"outperforms":[144],"top-ranked":[146],"method":[147],"we":[148],"AV":[152],"SELD":[154],"DCASE":[158],"Challenge":[160],"without":[161],"model":[162],"ensemble.":[163],"Codes":[164],"available":[166],"at":[167],"https://github.com/Hong-Hengyi/MVANet-SELD.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
