{"id":"https://openalex.org/W2895350599","doi":"https://doi.org/10.1145/3242969.3242973","title":"Estimating Visual Focus of Attention in Multiparty Meetings using Deep Convolutional Neural Networks","display_name":"Estimating Visual Focus of Attention in Multiparty Meetings using Deep Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2895350599","doi":"https://doi.org/10.1145/3242969.3242973","mag":"2895350599"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3242973","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3242973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","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/A5014373252","display_name":"Kazuhiro Otsuka","orcid":"https://orcid.org/0000-0003-4352-3955"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazuhiro Otsuka","raw_affiliation_strings":["NTT Corporation, Atsugi-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Atsugi-shi, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084720640","display_name":"Keisuke Kasuga","orcid":null},"institutions":[{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kasuga","raw_affiliation_strings":["Nagaoka University of Technology & NTT Communication Science Labs, Nagaoka-shi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology & NTT Communication Science Labs, Nagaoka-shi, Japan","institution_ids":["https://openalex.org/I85922643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102312930","display_name":"Martina K\u00f6hler","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martina K\u00f6hler","raw_affiliation_strings":["University of T\u00fcbingen & NTT Communication Science Labs, Tuebingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen & NTT Communication Science Labs, Tuebingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014373252"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.259,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88364516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9869999885559082,"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/T11094","display_name":"Face Recognition and Perception","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7770200967788696},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7293592095375061},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7234470248222351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7007344365119934},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6443376541137695},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5818507671356201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4671696126461029},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4560508728027344},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4434290826320648},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4423459470272064},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4162619411945343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3437011241912842},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3314695954322815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770200967788696},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7293592095375061},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7234470248222351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7007344365119934},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6443376541137695},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5818507671356201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4671696126461029},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4560508728027344},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4434290826320648},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4423459470272064},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4162619411945343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3437011241912842},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3314695954322815},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3242969.3242973","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3242973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W119403003","https://openalex.org/W1493372482","https://openalex.org/W1563178652","https://openalex.org/W1591474362","https://openalex.org/W1595229305","https://openalex.org/W1855879034","https://openalex.org/W1963882359","https://openalex.org/W1964725106","https://openalex.org/W1973672195","https://openalex.org/W1985479696","https://openalex.org/W1987411016","https://openalex.org/W1995562189","https://openalex.org/W2002261403","https://openalex.org/W2019989248","https://openalex.org/W2043393794","https://openalex.org/W2064675550","https://openalex.org/W2076897591","https://openalex.org/W2081841744","https://openalex.org/W2087652715","https://openalex.org/W2105889057","https://openalex.org/W2118924889","https://openalex.org/W2120615054","https://openalex.org/W2134794775","https://openalex.org/W2135002326","https://openalex.org/W2146507038","https://openalex.org/W2157623479","https://openalex.org/W2163605009","https://openalex.org/W2171757151","https://openalex.org/W2200813474","https://openalex.org/W2268304078","https://openalex.org/W2270470215","https://openalex.org/W2288074780","https://openalex.org/W2344284192","https://openalex.org/W2395639500","https://openalex.org/W2513140567","https://openalex.org/W2557283755","https://openalex.org/W2604352584","https://openalex.org/W2608133096","https://openalex.org/W2746759718","https://openalex.org/W2751594996","https://openalex.org/W2755598671","https://openalex.org/W2767781647","https://openalex.org/W2912500072","https://openalex.org/W2949667497","https://openalex.org/W2965385724"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W3207760378","https://openalex.org/W2562758970","https://openalex.org/W1986970529","https://openalex.org/W2161294397","https://openalex.org/W2012644758","https://openalex.org/W1996690921"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4],"employed":[5],"to":[6,71,81,88,166,214],"estimate":[7,90],"the":[8,24,35,43,72,84,91,100,104,113,124,135,140,143,152,161,167,173,220,224],"visual":[9],"focus":[10,48],"of":[11,26,34,39,45,51,94,212,216],"attention":[12],"(VFoA),":[13],"also":[14],"called":[15],"gaze":[16,92],"direction":[17,33,145],",":[18],"in":[19,108,171,181],"multiparty":[20,54,194],"face-to-face":[21],"meetings":[22],"on":[23,49,139],"basis":[25],"multimodal":[27,52],"nonverbal":[28],"behaviors":[29],"including":[30,56],"head":[31],"pose,":[32],"eyeball,":[36],"and":[37,53,61,193],"presence/absence":[38],"utterance.":[40],"To":[41],"reveal":[42],"potential":[44],"CNNs,":[46],"we":[47],"aspects":[50],"fusion":[55],"individual/group":[57],"models,":[58,183],"early/late":[59],"fusion,":[60,186],"robustness":[62],"when":[63,112],"using":[64],"inputs":[65,114],"from":[66],"image-based":[67,205],"trackers.":[68],"In":[69,158],"contrast":[70],"individual":[73,105,162,190],"model":[74,86,102,106,127,163],"that":[75,99,123,180,204,215,223],"separately":[76],"targets":[77],"each":[78],"person":[79],"specific":[80],"one's":[82],"seat,":[83],"group":[85,101,125,168,182],"aims":[87],"jointly":[89],"directions":[93],"all":[95],"participants.":[96],"Experiments":[97],"confirmed":[98,203],"outperformed":[103,151,197],"especially":[107],"predicting":[109],"listeners'":[110,136],"VFoA":[111,231],"did":[115],"not":[116],"include":[117],"eyeball":[118,144],"directions.":[119],"This":[120],"result":[121],"indicates":[122],"CNN":[126,225],"can":[128,207],"implicitly":[129],"learn":[130],"underlying":[131],"conversation":[132],"structures,":[133],"e.g.,":[134],"gazes":[137],"converge":[138],"speaker.":[141],"When":[142],"feature":[146],"is":[147,226],"available,":[148],"both":[149],"models":[150,154],"Bayes":[153],"used":[155],"for":[156,230],"comparison.":[157],"this":[159],"case,":[160],"was":[164,178],"superior":[165],"model,":[169],"particularly":[170],"estimating":[172],"speaker's":[174],"VFoA.":[175],"Moreover,":[176],"it":[177],"revealed":[179],"two-stage":[184],"late":[185],"which":[187],"integrates":[188],"an":[189],"features":[191,195],"first,":[192],"second,":[196],"other":[198],"structures.":[199],"Furthermore,":[200],"our":[201],"experiment":[202],"tracking":[206],"provide":[208],"a":[209,227],"comparable":[210],"level":[211],"performance":[213],"sensor-based":[217],"measurements.":[218],"Overall,":[219],"results":[221],"suggest":[222],"promising":[228],"approach":[229],"estimation.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}