{"id":"https://openalex.org/W4414032899","doi":"https://doi.org/10.1109/tnnls.2025.3600878","title":"Fine-Grained Audio\u2013Visual Event Localization","display_name":"Fine-Grained Audio\u2013Visual Event Localization","publication_year":2025,"publication_date":"2025-09-04","ids":{"openalex":"https://openalex.org/W4414032899","doi":"https://doi.org/10.1109/tnnls.2025.3600878","pmid":"https://pubmed.ncbi.nlm.nih.gov/40907051"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3600878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3600878","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5017156592","display_name":"Baoyu Fan","orcid":"https://orcid.org/0009-0005-5223-6183"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baoyu Fan","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396448","display_name":"Lu Liu","orcid":"https://orcid.org/0000-0001-5461-6706"},"institutions":[{"id":"https://openalex.org/I4210112302","display_name":"Coal Industry Jinan Design & Research Institute (China)","ror":"https://ror.org/023jx0404","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210112302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Liu","raw_affiliation_strings":["IEIT Systems Company Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"IEIT Systems Company Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210112302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616811","display_name":"Xiaochuan Li","orcid":"https://orcid.org/0000-0001-6143-0854"},"institutions":[{"id":"https://openalex.org/I4210112302","display_name":"Coal Industry Jinan Design & Research Institute (China)","ror":"https://ror.org/023jx0404","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210112302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochuan Li","raw_affiliation_strings":["IEIT Systems Company Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"IEIT Systems Company Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210112302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101549172","display_name":"Runze Zhang","orcid":"https://orcid.org/0009-0003-6318-3342"},"institutions":[{"id":"https://openalex.org/I4210112302","display_name":"Coal Industry Jinan Design & Research Institute (China)","ror":"https://ror.org/023jx0404","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210112302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Zhang","raw_affiliation_strings":["IEIT Systems Company Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"IEIT Systems Company Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210112302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103651635","display_name":"Liang Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112302","display_name":"Coal Industry Jinan Design & Research Institute (China)","ror":"https://ror.org/023jx0404","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210112302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Jin","raw_affiliation_strings":["IEIT Systems Company Ltd., Jinan, China"],"affiliations":[{"raw_affiliation_string":"IEIT Systems Company Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210112302"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101829311","display_name":"Jin Zhang","orcid":"https://orcid.org/0000-0001-9086-1178"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zhang","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017156592"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35571071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"1","first_page":"52","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9714999794960022,"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":0.9381999969482422,"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/audio-visual","display_name":"Audio visual","score":0.7742899656295776},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6280908584594727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.593641459941864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.340143084526062},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24503210186958313},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.048188239336013794}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7742899656295776},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6280908584594727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593641459941864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.340143084526062},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24503210186958313},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.048188239336013794},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3600878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3600878","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40907051","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40907051","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1968130034","https://openalex.org/W2036147067","https://openalex.org/W2125479168","https://openalex.org/W2126579184","https://openalex.org/W2173180041","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2618799552","https://openalex.org/W2619697695","https://openalex.org/W2625366777","https://openalex.org/W2737725206","https://openalex.org/W2884293275","https://openalex.org/W2962677524","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2963524571","https://openalex.org/W2963758027","https://openalex.org/W2964109005","https://openalex.org/W2983918066","https://openalex.org/W2990113535","https://openalex.org/W3015371781","https://openalex.org/W3034623254","https://openalex.org/W3035356601","https://openalex.org/W3093287838","https://openalex.org/W3106041614","https://openalex.org/W3118120400","https://openalex.org/W3175514052","https://openalex.org/W3195486004","https://openalex.org/W3196974791","https://openalex.org/W3198371949","https://openalex.org/W3213192039","https://openalex.org/W3214311327","https://openalex.org/W4211154280","https://openalex.org/W4286212078","https://openalex.org/W4297697565","https://openalex.org/W4304080723","https://openalex.org/W4307838488","https://openalex.org/W4312317576","https://openalex.org/W4312383651","https://openalex.org/W4312415534","https://openalex.org/W4312419390","https://openalex.org/W4312508181","https://openalex.org/W4313050661","https://openalex.org/W4362692581","https://openalex.org/W4367146821","https://openalex.org/W4372260310","https://openalex.org/W4382462080","https://openalex.org/W4384820833","https://openalex.org/W4386057769","https://openalex.org/W4386065620","https://openalex.org/W4386066074","https://openalex.org/W4386076085","https://openalex.org/W4386973893","https://openalex.org/W4387682108","https://openalex.org/W4387968342","https://openalex.org/W4389519587","https://openalex.org/W4392405713","https://openalex.org/W4399431911","https://openalex.org/W4402754197","https://openalex.org/W4403791272"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"Audio-visual":[0],"event":[1,83,115,136,141],"localization":[2,137],"(AVEL)":[3],"aims":[4],"to":[5,31,51,74,157,204],"recognize":[6],"events":[7,15,27,106,151],"in":[8,17,35],"videos":[9,91],"by":[10],"associating":[11],"audio-visual":[12,82,103,212],"information.":[13],"However,":[14,42],"involved":[16],"existing":[18,176],"AVEL":[19,71],"tasks":[20],"are":[21,28,48,107,117,124,152],"usually":[22],"coarse-grained":[23,57],"events.":[24,58,104],"Actually,":[25],"finer-grained":[26],"sometimes":[29],"necessary":[30],"be":[32,158],"distinguished,":[33],"especially":[34],"certain":[36],"expert-level":[37],"applications":[38],"or":[39,53],"rich-content-generation":[40],"studies.":[41],"this":[43,62,200],"is":[44,86],"challenging":[45],"because":[46],"they":[47],"more":[49,153],"difficult":[50],"detect":[52],"distinguish":[54],"compared":[55],"with":[56,126],"To":[59],"better":[60],"address":[61],"problem,":[63],"we":[64,77,131,161],"discuss":[65],"a":[66,133],"new":[67,134],"setting":[68],"of":[69,92,174,194,207,211],"fine-grained":[70,81,125,135,150,172],"from":[72,109,120,182,187],"dataset":[73,170],"method.":[75,196],"First,":[76],"constructed":[78],"the":[79,114,147,167,192,205],"first":[80],"dataset,":[84],"which":[85,123,144],"called":[87],"IT-AVE,":[88],"relying":[89],"on":[90,146,166],"playing":[93,121],"musical":[94],"instruments,":[95],"containing":[96],"13k":[97],"video":[98,140],"clips":[99],"and":[100,113,155,184],"over":[101],"52k":[102],"All":[105],"labeled":[108],"professional":[110],"music":[111],"practitioners,":[112],"categories":[116],"all":[118],"derived":[119,181,186],"techniques,":[122],"little":[127],"interclass":[128],"variation.":[129],"Next,":[130],"designed":[132],"method,":[138],"spatial-temporal":[139],"detector":[142],"(SVED),":[143],"focuses":[145],"challenges":[148],"that":[149,199],"imperceptible":[154],"prone":[156],"disturbed.":[159],"Finally,":[160],"conduct":[162],"extensive":[163],"experiments":[164],"based":[165],"proposed":[168],"IT-AVE":[169],"versus":[171],"versions":[173],"two":[175],"related":[177],"datasets,":[178],"including":[179],"UnAV-22":[180],"UnAV-100":[183],"FineAction-AV":[185],"FineAction.":[188],"Experimental":[189],"results":[190],"demonstrate":[191],"effectiveness":[193],"our":[195],"We":[197],"hope":[198],"work":[201],"will":[202],"contribute":[203],"exploration":[206],"an":[208],"integrated":[209],"understanding":[210],"videos.":[213]},"counts_by_year":[],"updated_date":"2026-01-10T23:39:48.068659","created_date":"2025-10-10T00:00:00"}