{"id":"https://openalex.org/W2036931953","doi":"https://doi.org/10.1145/2671188.2749396","title":"Audio-Based Multimedia Event Detection with DNNs and Sparse Sampling","display_name":"Audio-Based Multimedia Event Detection with DNNs and Sparse Sampling","publication_year":2015,"publication_date":"2015-06-22","ids":{"openalex":"https://openalex.org/W2036931953","doi":"https://doi.org/10.1145/2671188.2749396","mag":"2036931953"},"language":"en","primary_location":{"id":"doi:10.1145/2671188.2749396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2671188.2749396","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2671188.2749396","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2671188.2749396","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102832871","display_name":"Khalid Ashraf","orcid":"https://orcid.org/0000-0003-2247-5333"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalid Ashraf","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"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/A5031485831","display_name":"Forrest Iandola","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forrest Iandola","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076613173","display_name":"Matthew W. Moskewicz","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Moskewicz","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"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":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9158,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93310687,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"611","last_page":"614"},"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":0.9998999834060669,"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":0.9975000023841858,"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":0.8556536436080933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6110612750053406},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6074137091636658},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5909071564674377},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5620121955871582},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5492423176765442},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45828336477279663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4404542148113251},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4326742887496948},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4312017261981964},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4243502616882324},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4100600779056549},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.37684839963912964},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33795231580734253},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10569742321968079},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08697646856307983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556536436080933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6110612750053406},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6074137091636658},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5909071564674377},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5620121955871582},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5492423176765442},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45828336477279663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4404542148113251},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4326742887496948},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4312017261981964},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4243502616882324},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4100600779056549},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.37684839963912964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33795231580734253},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10569742321968079},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08697646856307983},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2671188.2749396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2671188.2749396","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2671188.2749396","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2671188.2749396","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2671188.2749396","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2671188.2749396","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1088636562","display_name":null,"funder_award_id":"DE-AC52-07-NA27344","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1356433355","display_name":null,"funder_award_id":"DE\u2010AC5207NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G14554683","display_name":null,"funder_award_id":"DEAC5207NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1974706823","display_name":null,"funder_award_id":"Contract DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G2145270357","display_name":null,"funder_award_id":"AC52\u201007NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G217780377","display_name":null,"funder_award_id":"DE-AC52-07-NA27344","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G4343739756","display_name":null,"funder_award_id":"Contract DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G5913291779","display_name":"BIGDATA: Small: DCM: DA: Collaborative Research: SMASH -- Scalable Multimedia content AnalysiS in a High-level language","funder_award_id":"1251276","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G69709960","display_name":null,"funder_award_id":"Contract DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G991281326","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2036931953.pdf","grobid_xml":"https://content.openalex.org/works/W2036931953.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1840102018","https://openalex.org/W2018951638","https://openalex.org/W2097508275","https://openalex.org/W2138445151","https://openalex.org/W2155893237","https://openalex.org/W2184801855","https://openalex.org/W2290542723","https://openalex.org/W2395981916","https://openalex.org/W2402668451","https://openalex.org/W2577570599","https://openalex.org/W2915649242","https://openalex.org/W2917553248","https://openalex.org/W3022392334"],"related_works":["https://openalex.org/W4321369474","https://openalex.org/W4312417841","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W4200173597","https://openalex.org/W3116150086","https://openalex.org/W2999805992","https://openalex.org/W4291897433","https://openalex.org/W3011074480","https://openalex.org/W3196649088"],"abstract_inverted_index":{"This":[0,125],"paper":[1],"presents":[2],"advances":[3],"in":[4,12,103,111,127,136,147,172,215],"analyzing":[5],"audio":[6,29,70,88],"content":[7],"information":[8],"to":[9,120,132,185],"detect":[10],"events":[11],"videos,":[13],"such":[14],"as":[15,118],"a":[16,19,24,55,76,86,99,108,133,144,165,186,192,206],"parade":[17],"or":[18],"birthday":[20],"party.":[21],"We":[22,97,150],"developed":[23],"set":[25],"of":[26,52,114,139],"tools":[27],"for":[28,46,57,64,175,202],"processing":[30,203],"within":[31],"the":[32,47,50,68,112,122,137,140,155,173],"predominantly":[33],"vision-focused":[34],"deep":[35],"neural":[36],"network":[37],"(DNN)":[38],"framework":[39],"Caffe.":[40],"Using":[41],"these":[42],"tools,":[43],"we":[44,80],"show,":[45],"first":[48],"time,":[49],"potential":[51],"using":[53,67,121,154],"only":[54],"DNN":[56,141],"audio-based":[58],"multimedia":[59],"event":[60,65,104],"detection.":[61],"Training":[62],"DNNs":[63],"detection":[66],"entire":[69,123],"track":[71],"from":[72],"each":[73],"video":[74],"causes":[75],"computational":[77,195],"bottleneck.":[78],"Here,":[79],"address":[81],"this":[82],"problem":[83],"by":[84],"developing":[85],"sparse":[87],"frame-sampling":[89],"method":[90,153],"that":[91],"improves":[92],"event-detection":[93],"speed":[94,198],"and":[95,143,160,168,209],"accuracy.":[96],"achieved":[98],"10":[100],"percentage-point":[101],"improvement":[102,199],"classification":[105],"accuracy,":[106],"with":[107,164,169],"200x":[109],"reduction":[110,126,135,146],"number":[113],"training":[115,148],"input":[116,128],"examples":[117],"compared":[119,161,184],"track.":[124],"feature":[129],"volume":[130],"led":[131],"16x":[134],"size":[138],"architecture":[142],"300x":[145],"time.":[149],"applied":[151],"our":[152,162],"recently":[156],"released":[157],"YLI-MED":[158],"dataset":[159],"results":[163,170,178],"state-of-the-art":[166],"system":[167,189],"reported":[171],"literature":[174],"TRECVIDMED.":[176],"Our":[177],"show":[179],"much":[180],"higher":[181],"MAP":[182],"scores":[183],"baseline":[187],"i-vector":[188],"-":[190],"at":[191],"significantly":[193],"reduced":[194],"cost.":[196],"The":[197],"is":[200],"relevant":[201],"videos":[204],"on":[205],"large":[207],"scale,":[208],"could":[210],"enable":[211],"more":[212],"effective":[213],"deployment":[214],"mobile":[216],"systems.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}