{"id":"https://openalex.org/W2009112943","doi":"https://doi.org/10.1145/1816041.1816057","title":"Coherent bag-of audio words model for efficient large-scale video copy detection","display_name":"Coherent bag-of audio words model for efficient large-scale video copy detection","publication_year":2010,"publication_date":"2010-07-05","ids":{"openalex":"https://openalex.org/W2009112943","doi":"https://doi.org/10.1145/1816041.1816057","mag":"2009112943"},"language":"en","primary_location":{"id":"doi:10.1145/1816041.1816057","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816041.1816057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Image and Video Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7525&context=sis_research","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100356241","display_name":"Yang Liu","orcid":"https://orcid.org/0009-0008-1519-3788"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101660306","display_name":"Wan\u2010Lei Zhao","orcid":"https://orcid.org/0000-0002-7915-447X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wan-Lei Zhao","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong","City University of Hong Kong , Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong , Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010722442","display_name":"Chong\u2010Wah Ngo","orcid":"https://orcid.org/0000-0003-4182-8261"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chong-Wah Ngo","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong","City University of Hong Kong , Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong , Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang-Sheng Xu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100511737","display_name":"Hanqing Lu","orcid":"https://orcid.org/0000-0001-9506-3407"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han-Qing Lu","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100356241"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":5.8185,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96506229,"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":"89","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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":0.8396568298339844},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6901552081108093},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6687549948692322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816026926040649},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5579215288162231},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5305383801460266},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5138921737670898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5081980228424072},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47832274436950684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38412538170814514},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3516865074634552},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.33380597829818726},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2669055461883545},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.23713505268096924},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.19551652669906616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8396568298339844},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6901552081108093},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6687549948692322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816026926040649},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5579215288162231},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5305383801460266},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5138921737670898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5081980228424072},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47832274436950684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38412538170814514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3516865074634552},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.33380597829818726},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2669055461883545},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.23713505268096924},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.19551652669906616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1816041.1816057","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816041.1816057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Image and Video Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7525","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7525&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/1816041.1816057","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7525","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7525&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/1816041.1816057","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1067081754","display_name":null,"funder_award_id":"7002438","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"},{"id":"https://openalex.org/G6212538874","display_name":null,"funder_award_id":"6.08E+15","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6229080522","display_name":null,"funder_award_id":"2010CB32905","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G7079452640","display_name":null,"funder_award_id":"CityU 119508","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1556531089","https://openalex.org/W1586255639","https://openalex.org/W1677409904","https://openalex.org/W1983364709","https://openalex.org/W1999956262","https://openalex.org/W2018369373","https://openalex.org/W2022303741","https://openalex.org/W2044139120","https://openalex.org/W2075854571","https://openalex.org/W2119577488","https://openalex.org/W2119605622","https://openalex.org/W2131846894","https://openalex.org/W2137075158","https://openalex.org/W2145291599","https://openalex.org/W2145400576","https://openalex.org/W2151103935","https://openalex.org/W2156617053","https://openalex.org/W2162672700","https://openalex.org/W2527334262"],"related_works":["https://openalex.org/W2131156500","https://openalex.org/W2118916824","https://openalex.org/W1546240199","https://openalex.org/W3159882232","https://openalex.org/W1911859126","https://openalex.org/W46679383","https://openalex.org/W57476147","https://openalex.org/W1969715806","https://openalex.org/W4241650944","https://openalex.org/W1479881079"],"abstract_inverted_index":{"Current":[0],"content-based":[1],"video":[2,25,185,209],"copy":[3,26,175,186,210],"detection":[4,27,187],"approaches":[5],"mostly":[6],"concentrate":[7],"on":[8,216],"the":[9,14,24,86,130,140,168,174,217],"visual":[10,40,49,192,206],"cues":[11,193],"and":[12,82,100,145,191,205,223],"neglect":[13],"audio":[15,31,54,63,70,117,149,162,190,204],"information.":[16],"In":[17,180],"this":[18],"paper,":[19],"we":[20,182],"attempt":[21],"to":[22,30,60,79,96,147,157,200],"tackle":[23],"task":[28],"resorting":[29],"information,":[32],"which":[33],"is":[34,58,74,94,154,171],"equivalently":[35],"important":[36],"as":[37,39,173],"well":[38],"information":[41,207],"in":[42,177,208],"multimedia":[43],"processing.":[44],"Firstly,":[45],"inspired":[46],"by":[47,119,194],"bag-of":[48,53],"words":[50,55],"model,":[51,88],"a":[52,75,89],"(BoA)":[56],"representation":[57],"proposed":[59],"characterize":[61],"each":[62],"frame.":[64],"Different":[65],"from":[66,160,188],"naive":[67],"single-based":[68],"modeling":[69],"retrieval":[71],"approaches,":[72],"BoA":[73,87,141],"high-level":[76],"model":[77,142],"due":[78],"its":[80],"perceptual":[81],"semantical":[83],"property.":[84],"Within":[85],"coherency":[90,111,132,137],"vocabulary":[91,105,112,138],"indexing":[92,102],"structure":[93],"adopted":[95],"achieve":[97],"more":[98,143],"efficient":[99],"effective":[101],"than":[103],"single":[104],"of":[106,115,122,203,220],"standard":[107],"BoW":[108],"model.":[109],"The":[110,164],"takes":[113],"advantage":[114],"multiple":[116],"features":[118],"computing":[120],"co-occurrence":[121],"them":[123],"across":[124,134],"different":[125],"feature":[126,135],"spaces.":[127],"By":[128],"enforcing":[129],"tight":[131],"constraint":[133],"spaces,":[136],"makes":[139],"discriminative":[144],"robust":[146],"various":[148],"transforms.":[150],"2D":[151],"Hough":[152],"transform":[153],"then":[155],"applied":[156],"aggregate":[158],"scores":[159],"matched":[161],"segments.":[163],"segements":[165],"fall":[166],"into":[167],"peak":[169],"bin":[170],"identified":[172],"segments":[176],"reference":[178],"video.":[179],"addition,":[181],"also":[183],"accomplish":[184],"both":[189],"performing":[195],"four":[196],"late":[197],"fusion":[198],"strategies":[199],"demonstrate":[201],"complementarity":[202],"detection.":[211],"Intensive":[212],"experiments":[213],"are":[214,226],"conducted":[215],"large-scale":[218],"dataset":[219],"TRECVID":[221],"2009":[222],"competitve":[224],"results":[225],"achieved.":[227]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}