{"id":"https://openalex.org/W1983018143","doi":"https://doi.org/10.1145/2647868.2654934","title":"Say Cheese vs. Smile","display_name":"Say Cheese vs. Smile","publication_year":2014,"publication_date":"2014-10-31","ids":{"openalex":"https://openalex.org/W1983018143","doi":"https://doi.org/10.1145/2647868.2654934","mag":"1983018143"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5070976231","display_name":"Yelin Kim","orcid":"https://orcid.org/0000-0002-6503-4637"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yelin Kim","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003136334","display_name":"Emily Mower Provost","orcid":"https://orcid.org/0000-0003-1870-6063"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Mower Provost","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070976231"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.7333,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92195692,"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":"27","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9986000061035156,"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":0.9947999715805054,"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/segmentation","display_name":"Segmentation","score":0.8293627500534058},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7214910984039307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6976280212402344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5798358917236328},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.561999499797821},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5504645705223083},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5368747115135193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5058667063713074},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.45119261741638184},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.42797982692718506},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.41396594047546387},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.4138963222503662},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27527907490730286},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.0873514711856842},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07160848379135132}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8293627500534058},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214910984039307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6976280212402344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5798358917236328},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.561999499797821},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5504645705223083},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5368747115135193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5058667063713074},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.45119261741638184},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.42797982692718506},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.41396594047546387},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4138963222503662},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27527907490730286},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.0873514711856842},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07160848379135132},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":1,"locations":[{"id":"doi:10.1145/2647868.2654934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2982580385","display_name":null,"funder_award_id":"RI-1217183","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W47265595","https://openalex.org/W170282027","https://openalex.org/W1586674080","https://openalex.org/W1668904664","https://openalex.org/W1736374775","https://openalex.org/W1824088427","https://openalex.org/W1966512492","https://openalex.org/W1981398125","https://openalex.org/W1983703866","https://openalex.org/W1984333007","https://openalex.org/W2017208747","https://openalex.org/W2018506469","https://openalex.org/W2074788634","https://openalex.org/W2080289724","https://openalex.org/W2089787547","https://openalex.org/W2093174546","https://openalex.org/W2108482774","https://openalex.org/W2117752179","https://openalex.org/W2128160875","https://openalex.org/W2137883513","https://openalex.org/W2142233983","https://openalex.org/W2143353756","https://openalex.org/W2146334809","https://openalex.org/W2150931957","https://openalex.org/W2153957661","https://openalex.org/W2156503193","https://openalex.org/W2161846515","https://openalex.org/W2162880944","https://openalex.org/W2167277498","https://openalex.org/W2169166781","https://openalex.org/W2558906580","https://openalex.org/W2602024037","https://openalex.org/W2622235196","https://openalex.org/W3144828656","https://openalex.org/W4301045096","https://openalex.org/W4386313974","https://openalex.org/W6637112759","https://openalex.org/W6680957919","https://openalex.org/W6681222889"],"related_works":["https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W2584926856","https://openalex.org/W2075935902","https://openalex.org/W3214419959","https://openalex.org/W2014713986","https://openalex.org/W4235619736","https://openalex.org/W3036279411","https://openalex.org/W4212815228","https://openalex.org/W114226241"],"abstract_inverted_index":{"Facial":[0,10],"movement":[1],"is":[2,29],"modulated":[3],"both":[4],"by":[5],"emotion":[6,11,87,164],"and":[7,50,68,82,118,138,157],"speech":[8,161],"articulation.":[9],"recognition":[12],"systems":[13,54],"aim":[14,28],"to":[15,144],"discriminate":[16],"between":[17,112],"emotions,":[18],"while":[19],"reducing":[20],"the":[21,76,105,109,131,135,158],"speech-related":[22],"variability":[23,162],"in":[24],"facial":[25,39,86,154],"cues.":[26],"This":[27,147],"often":[30],"achieved":[31],"using":[32],"two":[33],"key":[34],"features:":[35],"(1)":[36],"phoneme":[37,49,119,139],"segmentation:":[38],"cues":[40],"are":[41,142],"temporally":[42],"divided":[43],"into":[44,152],"units":[45],"with":[46,58],"a":[47,113,122],"single":[48],"(2)":[51],"phoneme-specific":[52],"classification:":[53],"learn":[55],"patterns":[56],"associated":[57],"groups":[59],"of":[60,78,160],"visually":[61],"similar":[62,143],"phonemes":[63],"(visemes),":[64],"e.g.":[65],"P,":[66],"B,":[67],"M.":[69],"In":[70],"this":[71],"work,":[72],"we":[73],"empirically":[74],"compare":[75],"effects":[77],"different":[79],"temporal":[80],"segmentation":[81,93,140,156],"classification":[83],"schemes":[84],"for":[85],"recognition.":[88],"We":[89,102,127],"propose":[90],"an":[91],"unsupervised":[92,137,153],"method":[94,107,117],"that":[95,104,130],"does":[96],"not":[97],"necessitate":[98],"costly":[99],"phonetic":[100],"transcripts.":[101],"show":[103],"proposed":[106,136],"bridges":[108],"accuracy":[110],"gap":[111],"traditional":[114],"sliding":[115],"window":[116],"segmentation,":[120],"achieving":[121],"statistically":[123],"significant":[124],"performance":[125],"gain.":[126],"also":[128],"demonstrate":[129],"segments":[132],"derived":[133],"from":[134],"strategies":[141],"each":[145],"other.":[146],"paper":[148],"provides":[149],"new":[150],"insight":[151],"motion":[155],"impact":[159],"on":[163],"classification.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}