{"id":"https://openalex.org/W2150231871","doi":"https://doi.org/10.1109/icme.2004.1394641","title":"Design and evaluation of a music video summarization system","display_name":"Design and evaluation of a music video summarization system","publication_year":2005,"publication_date":"2005-03-21","ids":{"openalex":"https://openalex.org/W2150231871","doi":"https://doi.org/10.1109/icme.2004.1394641","mag":"2150231871"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2004.1394641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2004.1394641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)","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/A5070347219","display_name":"Lalitha Agnihotri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131230","display_name":"Philips (United States)","ror":"https://ror.org/03kw6wr76","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122849","https://openalex.org/I4210131230"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Agnihotri","raw_affiliation_strings":["Philips Research Laboratories, Briarcliff Manor, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Research Laboratories, Briarcliff Manor, NY, USA","institution_ids":["https://openalex.org/I4210131230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017119312","display_name":"Nevenka Dimitrova","orcid":"https://orcid.org/0000-0003-4091-9233"},"institutions":[{"id":"https://openalex.org/I4210131230","display_name":"Philips (United States)","ror":"https://ror.org/03kw6wr76","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122849","https://openalex.org/I4210131230"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Dimitrova","raw_affiliation_strings":["Philips Research Laboratories, Briarcliff Manor, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips Research Laboratories, Briarcliff Manor, NY, USA","institution_ids":["https://openalex.org/I4210131230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088235357","display_name":"John R. Kender","orcid":"https://orcid.org/0009-0009-2522-053X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.R. Kender","raw_affiliation_strings":["Department of Computer Science, Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3773,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90195574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1943","last_page":"1946"},"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":0.9983999729156494,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9926000237464905,"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":0.8277423977851868},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.807162880897522},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.7221484780311584},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.518912136554718},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4597587287425995},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42463892698287964},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41567301750183105},{"id":"https://openalex.org/keywords/palette","display_name":"Palette (painting)","score":0.4107773005962372},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40530529618263245},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33019888401031494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277423977851868},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.807162880897522},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.7221484780311584},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.518912136554718},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4597587287425995},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42463892698287964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41567301750183105},{"id":"https://openalex.org/C2779674283","wikidata":"https://www.wikidata.org/wiki/Q425548","display_name":"Palette (painting)","level":2,"score":0.4107773005962372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40530529618263245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33019888401031494},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2004.1394641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2004.1394641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1559992913","https://openalex.org/W1589182518","https://openalex.org/W1971493892","https://openalex.org/W1983032813","https://openalex.org/W2066610120","https://openalex.org/W2141854340","https://openalex.org/W2143235280","https://openalex.org/W2169790300","https://openalex.org/W6635336695"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W634160686","https://openalex.org/W2597614303","https://openalex.org/W2366403280","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580","https://openalex.org/W1495108544","https://openalex.org/W300569899"],"abstract_inverted_index":{"We":[0,67],"present":[1],"a":[2,16,23,146],"system":[3,97],"that":[4,47,177],"summarizes":[5],"the":[6,20,34,37,40,94,108,116,119,135,156,168,175],"textual,":[7],"audio,":[8],"and":[9,36,64,84,90,103,113,131,170],"video":[10,55,130],"information":[11,76],"of":[12,22,26,39,93,110,118,148,164,174],"music":[13,41,54],"videos":[14,51],"in":[15,60,115,161,167,171],"format":[17],"tuned":[18],"to":[19,142],"preferences":[21],"focus":[24],"group":[25],"20":[27],"users.":[28],"First,":[29],"we":[30,44,139],"analyzed":[31],"user-needs":[32],"for":[33],"content":[35,133,144,165],"layout":[38],"summaries.":[42],"Then,":[43],"designed":[45],"algorithms":[46],"segment":[48],"individual":[49],"song":[50,70],"from":[52,107,134],"full":[53],"programs":[56],"by":[57,145],"noting":[58],"changes":[59],"color":[61],"palette,":[62],"transcript,":[63],"audio":[65,89,132],"classification.":[66],"summarize":[68],"each":[69],"with":[71,100],"automatically":[72,98],"selected":[73],"high":[74,101],"level":[75],"such":[77],"as":[78,86,88],"title,":[79],"artist,":[80],"duration,":[81],"title":[82],"frame,":[83],"text":[85,117],"well":[87],"visual":[91],"segments":[92],"chorus.":[95],"Our":[96,122,150],"determines":[99],"recall":[102],"precision":[104],"chorus":[105],"locations,":[106],"placement":[109],"repeated":[111],"words":[112],"phrases":[114],"song's":[120],"lyrics.":[121],"Bayesian":[123],"belief":[124],"network":[125],"then":[126],"selects":[127],"other":[128],"significant":[129],"multiple":[136],"media.":[137],"Overall,":[138],"are":[140],"able":[141],"compress":[143],"factor":[147],"10.":[149],"second":[151],"user":[152],"study":[153],"has":[154],"identified":[155],"principal":[157],"variations":[158],"between":[159],"users":[160],"their":[162,172,180],"choices":[163,173],"desired":[166],"summary,":[169],"platforms":[176],"should":[178],"support":[179],"viewing.":[181]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
