{"id":"https://openalex.org/W1559922967","doi":"https://doi.org/10.21437/interspeech.2013-654","title":"Robust audio-codebooks for large-scale event detection in consumer videos","display_name":"Robust audio-codebooks for large-scale event detection in consumer videos","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W1559922967","doi":"https://doi.org/10.21437/interspeech.2013-654","mag":"1559922967"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-654","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Robust_Audio-Codebooks_for_Large-Scale_Event_Detection_in_Consumer_Videos/6473666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086192353","display_name":"Shourabh Rawat","orcid":"https://orcid.org/0009-0000-0160-3741"},"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":"Shourabh Rawat","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008492426","display_name":"Peter Schulam","orcid":null},"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":"Peter F. Schulam","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034672538","display_name":"Susanne Burger","orcid":null},"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":"Susanne Burger","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110183841","display_name":"Duo Ding","orcid":null},"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":"Duo Ding","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101401275","display_name":"Yipei Wang","orcid":"https://orcid.org/0000-0002-9589-7177"},"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":"Yipei Wang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2929","last_page":"2933"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7492705583572388},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5332545638084412},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4954427480697632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48698458075523376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43183547258377075},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32458215951919556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492705583572388},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5332545638084412},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4954427480697632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48698458075523376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43183547258377075},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32458215951919556},{"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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2013-654","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1092","is_oa":false,"landing_page_url":"http://repository.cmu.edu/lti/97","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473666","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:figshare.com:article/6473666","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Robust_Audio-Codebooks_for_Large-Scale_Event_Detection_in_Consumer_Videos/6473666","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473666.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473666.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473666","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Robust_Audio-Codebooks_for_Large-Scale_Event_Detection_in_Consumer_Videos/6473666","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1535031652","https://openalex.org/W1600745603","https://openalex.org/W1657975426","https://openalex.org/W1880262756","https://openalex.org/W1976610042","https://openalex.org/W2036718463","https://openalex.org/W2085662862","https://openalex.org/W2106241685","https://openalex.org/W2144037622","https://openalex.org/W2147147599","https://openalex.org/W2151259137","https://openalex.org/W2155490028","https://openalex.org/W2158226832","https://openalex.org/W2186804261","https://openalex.org/W2396707013","https://openalex.org/W2402668451","https://openalex.org/W2406196141","https://openalex.org/W2406257467","https://openalex.org/W2408491073"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2755342338","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2058170566"],"abstract_inverted_index":{"In":[0,83],"this":[1,84],"paper":[2],"we":[3,86,107,128,149,179],"present":[4],"our":[5,20,177,185],"audio":[6,45,96,125,138,187],"based":[7,152],"system":[8],"for":[9,98,119,133],"detecting":[10],"\"events\"":[11],"within":[12],"consumer":[13],"videos":[14],"(e.g.":[15],"You":[16],"Tube)":[17],"and":[18,30,44,47,79,94,115,135,140],"report":[19],"experiments":[21],"on":[22,60,65],"the":[23,49,66,99,109],"TRECVID":[24],"Multimedia":[25],"Event":[26],"Detection":[27],"(MED)":[28],"task":[29,100],"development":[31],"data.":[32],"Codebook":[33],"or":[34],"bag-of-words":[35],"models":[36,59],"have":[37],"been":[38],"widely":[39],"used":[40],"in":[41,51,124],"text,":[42],"visual":[43],"domains":[46],"form":[48],"state-of-the-art":[50],"MED":[52,102],"tasks.":[53],"The":[54],"overall":[55],"effectiveness":[56],"of":[57,68,81,101,165],"these":[58,174],"such":[61],"datasets":[62],"depends":[63],"critically":[64],"choice":[67,80],"lowlevel":[69],"features,":[70],"clustering":[71],"approach,":[72],"sampling":[73],"method,":[74],"codebook":[75],"size,":[76],"weighting":[77],"schemes":[78],"classifier.":[82],"work":[85],"empirically":[87],"evaluate":[88],"several":[89,130],"approaches":[90],"to":[91,145,159],"model":[92],"expressive":[93,137],"robust":[95],"codebooks":[97,139],"while":[103,169],"ensuring":[104],"compactness.":[105],"First,":[106],"introduce":[108],"Large":[110],"Scale":[111],"Pooling":[112],"Features":[113,118],"(LSPF)":[114],"Stacked":[116],"Cepstral":[117],"encoding":[120],"local":[121],"temporal":[122],"information":[123],"codebooks.":[126],"Second,":[127],"discuss":[129],"design":[131],"decisions":[132,175],"generating":[134],"representing":[136],"show":[141],"how":[142],"they":[143],"scale":[144],"large":[146],"datasets.":[147],"Third,":[148],"apply":[150],"text":[151],"techniques":[153],"like":[154],"Latent":[155],"Dirichlet":[156],"Allocation":[157],"(LDA)":[158],"learn":[160],"acoustic-topics":[161],"as":[162],"a":[163],"means":[164],"providing":[166],"compact":[167],"representation":[168],"maintaining":[170],"performance.":[171],"By":[172],"aggregating":[173],"into":[176],"model,":[178],"obtained":[180],"11%":[181],"relative":[182],"improvement":[183],"over":[184],"baseline":[186],"systems.":[188]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
