{"id":"https://openalex.org/W2098529386","doi":"https://doi.org/10.1109/icme.2005.1521455","title":"Estimation of Speaking Speed for Faster Face Detection in Video-Footage","display_name":"Estimation of Speaking Speed for Faster Face Detection in Video-Footage","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2098529386","doi":"https://doi.org/10.1109/icme.2005.1521455","mag":"2098529386"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","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/A5101630554","display_name":"Osamu Ikeda","orcid":"https://orcid.org/0000-0001-9128-1431"},"institutions":[{"id":"https://openalex.org/I7377986","display_name":"Takushoku University","ror":"https://ror.org/05qh38f12","country_code":"JP","type":"education","lineage":["https://openalex.org/I7377986"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"O. Ikeda","raw_affiliation_strings":["Faculty of Engineering, Takushoku University, Tokyo, Japan","Fac. of Eng., Takushoku Univ., Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Takushoku University, Tokyo, Japan","institution_ids":["https://openalex.org/I7377986"]},{"raw_affiliation_string":"Fac. of Eng., Takushoku Univ., Tokyo","institution_ids":["https://openalex.org/I7377986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101630554"],"corresponding_institution_ids":["https://openalex.org/I7377986"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.20458055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"83","issue":null,"first_page":"442","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10057","display_name":"Face and Expression Recognition","score":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9976999759674072,"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":0.8105834722518921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7540976405143738},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6757622957229614},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6584445238113403},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.608039140701294},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.5590046644210815},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.449311226606369},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43969637155532837},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43503594398498535},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.43299126625061035},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4276130795478821},{"id":"https://openalex.org/keywords/hsl-and-hsv","display_name":"HSL and HSV","score":0.4265802800655365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.342263400554657},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3409121036529541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32046276330947876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105834722518921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7540976405143738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6757622957229614},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6584445238113403},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.608039140701294},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.5590046644210815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.449311226606369},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43969637155532837},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43503594398498535},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.43299126625061035},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4276130795478821},{"id":"https://openalex.org/C36372059","wikidata":"https://www.wikidata.org/wiki/Q376492","display_name":"HSL and HSV","level":3,"score":0.4265802800655365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.342263400554657},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3409121036529541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32046276330947876},{"id":"https://openalex.org/C2522874641","wikidata":"https://www.wikidata.org/wiki/Q808","display_name":"Virus","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2005.1521455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1574019097","https://openalex.org/W1969228515","https://openalex.org/W1993625798","https://openalex.org/W2106603433","https://openalex.org/W2115689562","https://openalex.org/W2115886973","https://openalex.org/W2117793832","https://openalex.org/W2121601095","https://openalex.org/W2124351082","https://openalex.org/W2138451337","https://openalex.org/W2145073242","https://openalex.org/W2164598857","https://openalex.org/W2166713160","https://openalex.org/W2217896605","https://openalex.org/W3071838041","https://openalex.org/W6677621491","https://openalex.org/W6681651645"],"related_works":["https://openalex.org/W1555117740","https://openalex.org/W2336272890","https://openalex.org/W4308999381","https://openalex.org/W3183843611","https://openalex.org/W4312238398","https://openalex.org/W3211418293","https://openalex.org/W4308999963","https://openalex.org/W2163107586","https://openalex.org/W4285815683","https://openalex.org/W2056855147"],"abstract_inverted_index":{"We":[0],"previously":[1],"reported":[2],"a":[3,89,105,114,145],"face":[4,79,172],"detection":[5,43,80,170],"system":[6],"based":[7],"on":[8],"color":[9,18],"segmentation":[10,29,143],"using":[11,83],"HSV.":[12],"It":[13],"was":[14],"shown":[15],"that":[16],"the":[17,45,61,78,93,101,120,125,137,151,154,163],"is":[19,40,98,117,158],"more":[20],"effective":[21,33],"than":[22],"other":[23],"colors":[24],"not":[25],"only":[26],"in":[27,32,81,88],"accurate":[28],"but":[30],"also":[31],"extraction":[34],"of":[35,55,95,110,139,153,171],"facial":[36,69],"features.":[37],"The":[38],"first":[39],"crucial":[41],"for":[42,47,104,142],"and":[44,63,86,130,148],"latter":[46],"recognition.":[48],"When":[49],"it":[50],"comes":[51],"to":[52,124,127,135,144,149,167],"video":[53,62,87,108],"footages":[54],"news":[56],"program,":[57],"sound":[58,85],"often":[59],"accompanies":[60],"persons":[64],"express":[65],"themselves":[66],"by":[67,162],"moving":[68],"parts":[70],"while":[71],"speaking.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"improve":[77],"speed":[82],"both":[84],"combined":[90],"way.":[91],"First,":[92],"rate":[94,126],"syllables":[96],"spoken":[97],"estimated":[99],"from":[100,160],"sound.":[102],"Next,":[103],"beginning":[106],"short":[107],"clip":[109],"each":[111],"new":[112],"scene,":[113],"differential":[115],"image":[116],"formed":[118],"with":[119],"frame":[121],"distance":[122],"corresponding":[123],"find":[128],"mouth":[129],"eyes.":[131],"This":[132],"enables":[133],"us":[134],"reduce":[136],"number":[138],"sampling":[140],"points":[141],"great":[146],"degree":[147],"enhance":[150],"reliability":[152],"detection.":[155],"Also,":[156],"music":[157],"discriminated":[159],"speaking":[161],"estimation.":[164],"These":[165],"contribute":[166],"much":[168],"faster":[169]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}