{"id":"https://openalex.org/W2412505962","doi":"https://doi.org/10.1145/2911996.2912048","title":"Recurrent Support Vector Machines for Audio-Based Multimedia Event Detection","display_name":"Recurrent Support Vector Machines for Audio-Based Multimedia Event Detection","publication_year":2016,"publication_date":"2016-06-06","ids":{"openalex":"https://openalex.org/W2412505962","doi":"https://doi.org/10.1145/2911996.2912048","mag":"2412505962"},"language":"en","primary_location":{"id":"doi:10.1145/2911996.2912048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911996.2912048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100377624","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-4749-2984"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6596,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.621054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8538228273391724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6578171253204346},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6325610280036926},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5801497101783752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551973283290863},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5096139907836914},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.48672059178352356},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4663827419281006},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4644107520580292},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4434582591056824},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4417962431907654},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4212597608566284},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41880345344543457},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4182608425617218},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3447139859199524},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3152254521846771}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538228273391724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6578171253204346},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6325610280036926},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5801497101783752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551973283290863},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5096139907836914},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.48672059178352356},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4663827419281006},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4644107520580292},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4434582591056824},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4417962431907654},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4212597608566284},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41880345344543457},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4182608425617218},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3447139859199524},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3152254521846771},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2911996.2912048","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911996.2912048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1535031652","https://openalex.org/W1559922967","https://openalex.org/W1600745603","https://openalex.org/W1650531274","https://openalex.org/W2018951638","https://openalex.org/W2036931953","https://openalex.org/W2043194666","https://openalex.org/W2064675550","https://openalex.org/W2075606539","https://openalex.org/W2090777335","https://openalex.org/W2097508275","https://openalex.org/W2109235804","https://openalex.org/W2118585731","https://openalex.org/W2144902422","https://openalex.org/W2145537345","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2152828142","https://openalex.org/W2396707013","https://openalex.org/W2398456099","https://openalex.org/W2400753342","https://openalex.org/W2402069222","https://openalex.org/W2402668451","https://openalex.org/W2406257467","https://openalex.org/W2407005679","https://openalex.org/W2408491073","https://openalex.org/W2963399116","https://openalex.org/W2990138404","https://openalex.org/W3001645704","https://openalex.org/W6681302627"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W3159882232","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Multimedia":[0],"event":[1,111],"detection":[2],"(MED)":[3],"is":[4,65],"the":[5,23,41,81,98,120],"task":[6],"of":[7,19,83,91],"detecting":[8],"given":[9],"events":[10],"(e.g.":[11],"parade,":[12],"birthday":[13],"party)":[14],"in":[15,48,68,80,113],"a":[16,34,75,85,89],"large":[17],"collection":[18],"video":[20],"clips.":[21],"While":[22],"most":[24],"useful":[25],"information":[26,62],"comes":[27],"from":[28,40],"visual":[29,51],"features":[30],"and":[31,52,133],"speech":[32,53],"recognition,":[33],"lot":[35],"can":[36],"also":[37],"be":[38],"inferred":[39],"non-speech":[42,60],"audio":[43,61],"content,":[44],"either":[45,84],"alone":[46],"or":[47,88,103],"conjunction":[49],"with":[50,59],"cues.":[54],"This":[55],"paper":[56],"studies":[57],"MED":[58,64],"only.":[63],"usually":[66],"performed":[67],"two":[69],"stages.":[70],"The":[71],"first":[72],"stage":[73,100,122],"generates":[74],"representation":[76],"for":[77,119],"each":[78,109,114],"clip":[79],"form":[82],"single":[86],"vector":[87,125],"sequence":[90],"vectors,":[92],"often":[93],"by":[94],"aggregating":[95],"frame-level":[96],"features;":[97],"second":[99,121],"performs":[101],"binary":[102],"multi-class":[104],"classification":[105],"to":[106],"decide":[107],"whether":[108],"target":[110],"occurs":[112],"clip.":[115],"Common":[116],"classifiers":[117],"used":[118],"include":[123],"support":[124],"machines":[126],"(SVMs),":[127],"feed-forward":[128],"deep":[129],"neural":[130,135],"networks":[131,136],"(DNNs),":[132],"recurrent":[134],"(RNNs).":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}