{"id":"https://openalex.org/W2018832017","doi":"https://doi.org/10.1145/2814815.2814816","title":"Insights into Audio-Based Multimedia Event Classification with Neural Networks","display_name":"Insights into Audio-Based Multimedia Event Classification with Neural Networks","publication_year":2015,"publication_date":"2015-10-30","ids":{"openalex":"https://openalex.org/W2018832017","doi":"https://doi.org/10.1145/2814815.2814816","mag":"2018832017"},"language":"en","primary_location":{"id":"doi:10.1145/2814815.2814816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2814815.2814816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Workshop on Community-Organized Multimodal Mining: Opportunities for Novel Solutions","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/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Fondazione Bruno Kessler, Trento, Italy","[Fondazione Bruno Kessler, Trento, (Italy)]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"[Fondazione Bruno Kessler, Trento, (Italy)]","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083402055","display_name":"Julia Bernd","orcid":"https://orcid.org/0000-0002-9792-2743"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Bernd","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73214985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"23"},"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":0.9898999929428101,"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":0.9868000149726868,"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":0.8740795850753784},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6801203489303589},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6396892070770264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.578752338886261},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5774921178817749},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5625928640365601},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5244298577308655},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.4796745777130127},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4681437611579895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45525017380714417},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45473653078079224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4439120888710022},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33912089467048645},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32684674859046936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740795850753784},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6801203489303589},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6396892070770264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578752338886261},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5774921178817749},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5625928640365601},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5244298577308655},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.4796745777130127},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4681437611579895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45525017380714417},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45473653078079224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4439120888710022},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33912089467048645},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32684674859046936},{"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},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2814815.2814816","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2814815.2814816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Workshop on Community-Organized Multimodal Mining: Opportunities for Novel Solutions","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/170445","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/170445","pdf_url":null,"source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/book"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1559401186","https://openalex.org/W1840102018","https://openalex.org/W2008415856","https://openalex.org/W2022011789","https://openalex.org/W2036931953","https://openalex.org/W2125838338","https://openalex.org/W2136922672","https://openalex.org/W2147627917","https://openalex.org/W2147768505","https://openalex.org/W2161893161","https://openalex.org/W2290542723","https://openalex.org/W2394571307","https://openalex.org/W2402069222","https://openalex.org/W2577570599","https://openalex.org/W2597289420","https://openalex.org/W2913932916","https://openalex.org/W2915722758","https://openalex.org/W2917553248","https://openalex.org/W2963399116","https://openalex.org/W6683819664","https://openalex.org/W6776952390"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2601133591","https://openalex.org/W1487808658"],"abstract_inverted_index":{"Multimedia":[0],"Event":[1],"Detection":[2],"(MED)":[3],"aims":[4],"to":[5,103,145,180],"identify":[6],"events-also":[7],"called":[8],"scenes-in":[9],"videos,":[10],"such":[11,25],"as":[12,26],"a":[13,17,117,135,159],"flash":[14],"mob":[15],"or":[16],"wedding":[18],"ceremony.":[19],"Audio":[20],"content":[21,28],"information":[22],"complements":[23],"cues":[24],"visual":[27],"and":[29,47,69,91,173],"text.":[30],"In":[31],"this":[32,55],"paper,":[33],"we":[34,107],"explore":[35,60,92],"the":[36,76,93,97,101,104,109,121,126,146,151,182],"optimization":[37],"of":[38,65,67,71,79,95,111,138],"neural":[39,161],"networks":[40],"(NNs)":[41],"for":[42,57,100,120],"audio-based":[43],"multimedia":[44],"event":[45,122],"classification,":[46],"discuss":[48],"some":[49],"insights":[50],"towards":[51],"more":[52,139],"effectively":[53],"using":[54],"paradigm":[56],"MED.":[58],"We":[59,73,124],"different":[61],"architectures,":[62],"in":[63,86,150],"terms":[64],"number":[66,70],"layers":[68],"neurons.":[72],"also":[74],"assess":[75],"performance":[77,110,136],"impact":[78],"pre-training":[80,175],"with":[81,88,116,158,163,170],"Restricted":[82],"Boltzmann":[83],"Machines":[84],"(RBMs)":[85],"contrast":[87],"random":[89,164],"initialization,":[90,165],"effect":[94],"varying":[96],"context":[98],"window":[99],"input":[102],"NNs.":[105],"Lastly,":[106],"compare":[108],"Hidden":[112],"Markov":[113],"Models":[114],"(HMMs)":[115],"discriminative":[118],"classifier":[119],"classification.":[123],"used":[125],"publicly":[127],"available":[128],"event-annotated":[129],"YLI-MED":[130],"dataset.":[131],"Our":[132],"results":[133,148,155],"showed":[134],"improvement":[137],"than":[140],"6%":[141],"absolute":[142],"accuracy":[143],"compared":[144],"latest":[147],"reported":[149],"literature.":[152],"Interestingly,":[153],"these":[154],"were":[156],"obtained":[157],"single-layer":[160],"network":[162],"suggesting":[166],"that":[167],"standard":[168],"approaches":[169],"deep":[171],"learning":[172],"RBM":[174],"are":[176],"not":[177],"fully":[178],"adequate":[179],"address":[181],"high-level":[183],"video":[184],"event-classification":[185],"task.":[186]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}