{"id":"https://openalex.org/W2510659016","doi":"https://doi.org/10.1109/tmm.2016.2608002","title":"Collective First-Person Vision for Automatic Gaze Analysis in Multiparty Conversations","display_name":"Collective First-Person Vision for Automatic Gaze Analysis in Multiparty Conversations","publication_year":2016,"publication_date":"2016-09-09","ids":{"openalex":"https://openalex.org/W2510659016","doi":"https://doi.org/10.1109/tmm.2016.2608002","mag":"2510659016"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2016.2608002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2016.2608002","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5059300000","display_name":"Shiro Kumano","orcid":"https://orcid.org/0000-0002-1231-5566"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shiro Kumano","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014373252","display_name":"Kazuhiro Otsuka","orcid":"https://orcid.org/0000-0003-4352-3955"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Otsuka","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101707623","display_name":"Ryo Ishii","orcid":"https://orcid.org/0000-0003-1025-1148"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Ishii","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017815880","display_name":"Junji Yamato","orcid":"https://orcid.org/0000-0003-1634-7984"},"institutions":[{"id":"https://openalex.org/I116465919","display_name":"Kogakuin University","ror":"https://ror.org/01wc2tq75","country_code":"JP","type":"education","lineage":["https://openalex.org/I116465919"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junji Yamato","raw_affiliation_strings":["Kogakuin University, Tokyo, Japan","Nippon Telegraph and Telephone Corporation, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kogakuin University, Tokyo, Japan","institution_ids":["https://openalex.org/I116465919"]},{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3466,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81724107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"1","first_page":"107","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9944000244140625,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.8650383949279785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8137721419334412},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7719060182571411},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.6423814296722412},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6331759095191956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6306155920028687},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5474005341529846},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4540780484676361},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.4475725293159485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40124621987342834},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39786097407341003},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1368710994720459},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1309392750263214},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07720226049423218}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8650383949279785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137721419334412},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7719060182571411},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.6423814296722412},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6331759095191956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306155920028687},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5474005341529846},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4540780484676361},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.4475725293159485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40124621987342834},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39786097407341003},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1368710994720459},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1309392750263214},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07720226049423218},{"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:10.1109/tmm.2016.2608002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2016.2608002","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W9931112","https://openalex.org/W32085468","https://openalex.org/W135919963","https://openalex.org/W140952618","https://openalex.org/W575657333","https://openalex.org/W1583773829","https://openalex.org/W1595229305","https://openalex.org/W1606844999","https://openalex.org/W1649998307","https://openalex.org/W1908082127","https://openalex.org/W1912797782","https://openalex.org/W1965305672","https://openalex.org/W1969320149","https://openalex.org/W1971251683","https://openalex.org/W1975879668","https://openalex.org/W1980083892","https://openalex.org/W1980307906","https://openalex.org/W1982794901","https://openalex.org/W1985479696","https://openalex.org/W1986712194","https://openalex.org/W1990930131","https://openalex.org/W1992724000","https://openalex.org/W1997471410","https://openalex.org/W1999633305","https://openalex.org/W2005628955","https://openalex.org/W2019989248","https://openalex.org/W2022995199","https://openalex.org/W2025239563","https://openalex.org/W2027151471","https://openalex.org/W2027879843","https://openalex.org/W2034382626","https://openalex.org/W2037557484","https://openalex.org/W2043033468","https://openalex.org/W2044632229","https://openalex.org/W2046496967","https://openalex.org/W2050517906","https://openalex.org/W2054684275","https://openalex.org/W2054802006","https://openalex.org/W2062000228","https://openalex.org/W2062242288","https://openalex.org/W2073188584","https://openalex.org/W2074520446","https://openalex.org/W2078088780","https://openalex.org/W2083049794","https://openalex.org/W2085261163","https://openalex.org/W2087652715","https://openalex.org/W2102481828","https://openalex.org/W2105889057","https://openalex.org/W2109722393","https://openalex.org/W2111930625","https://openalex.org/W2112731937","https://openalex.org/W2112793008","https://openalex.org/W2113510982","https://openalex.org/W2115011265","https://openalex.org/W2118924889","https://openalex.org/W2121972999","https://openalex.org/W2124211486","https://openalex.org/W2125277152","https://openalex.org/W2134794775","https://openalex.org/W2136668269","https://openalex.org/W2147806277","https://openalex.org/W2148839887","https://openalex.org/W2149382413","https://openalex.org/W2155479901","https://openalex.org/W2158192499","https://openalex.org/W2163915297","https://openalex.org/W2164598857","https://openalex.org/W2167020116","https://openalex.org/W2170505850","https://openalex.org/W2333605632","https://openalex.org/W2395639500","https://openalex.org/W2461911683","https://openalex.org/W2996868574","https://openalex.org/W3103419911","https://openalex.org/W3106262690","https://openalex.org/W4300718545","https://openalex.org/W6601279312","https://openalex.org/W6605818622","https://openalex.org/W6642889604","https://openalex.org/W6661806271","https://openalex.org/W6661885551","https://openalex.org/W6676662276","https://openalex.org/W6678494552"],"related_works":["https://openalex.org/W2480793735","https://openalex.org/W4384788979","https://openalex.org/W2511178891","https://openalex.org/W2126676984","https://openalex.org/W178060743","https://openalex.org/W2909390414","https://openalex.org/W2954509079","https://openalex.org/W2161294397","https://openalex.org/W2012644758","https://openalex.org/W3104472694"],"abstract_inverted_index":{"This":[0],"paper":[1],"targets":[2],"smallto":[3],"medium-sized-group":[4],"face-to-face":[5],"conversations":[6,146],"where":[7,46],"each":[8,154],"person":[9],"wears":[10],"a":[11,55,87,115,149,174,188,193],"dual-view":[12],"camera,":[13],"consisting":[14],"of":[15,82,124,151,158,169,178,201],"inwardand":[16],"outward-looking":[17],"cameras,":[18],"and":[19,52,73,132,161,204,208],"presents":[20],"an":[21,156],"almost":[22],"fully":[23],"automatic":[24],"but":[25],"accurate":[26],"ofline":[27],"gaze":[28,66,74,83,112,181],"analysis":[29],"framework":[30],"that":[31,92],"does":[32],"not":[33],"require":[34],"users":[35],"to":[36,96,148,171],"perform":[37],"any":[38],"calibration":[39],"steps.":[40],"Our":[41,197],"collective":[42],"first-person":[43],"vision":[44],"framework,":[45],"captured":[47],"audio-visual":[48],"signals":[49],"are":[50,94],"gathered":[51],"processed":[53],"in":[54,163,167,180,206,213],"centralized":[56],"system,":[57],"jointly":[58],"undertakes":[59],"the":[60,99,102,125,128,137],"fundamental":[61],"functions":[62],"required":[63],"for":[64,133],"group":[65,189],"analysis,":[67],"including":[68],"speaker":[69],"detection,":[70],"face":[71],"tracking,":[72],"tracking.":[75,182],"Of":[76],"particular":[77],"note":[78],"is":[79],"our":[80,107],"self-calibration":[81],"trackers":[84],"by":[85,164],"exploiting":[86],"general":[88],"conversation":[89,194],"rule,":[90],"namely":[91],"listeners":[93],"likely":[95],"look":[97],"at":[98,131],"speaker.":[100],"From":[101],"rough":[103],"conversational":[104],"prior":[105],"knowledge,":[106],"system":[108],"visualizes":[109],"fine-grained":[110],"participants'":[111],"behavior":[113],"as":[114],"gazee-centered":[116],"heat":[117],"map,":[118],"which":[119],"quantitatively":[120],"reveals":[121,186],"what":[122],"parts":[123],"gazee's":[126],"body":[127],"participant":[129],"looked":[130],"how":[134],"long":[135],"while":[136],"gazer":[138],"was":[139],"speaking":[140],"or":[141],"listening.":[142],"An":[143],"experiment":[144],"using":[145],"amounting":[147],"total":[150],"140":[152],"min,":[153],"lasting":[155],"average":[157],"8.7":[159],"min":[160],"engaged":[162],"37":[165],"participants":[166],"groups":[168],"three":[170],"six,":[172],"achieves":[173,199],"mean":[175],"absolute":[176],"error":[177],"2.8\u00b0":[179],"A":[183],"statistical":[184],"test":[185],"neither":[187],"size":[190],"effect":[191],"nor":[192],"type":[195],"effect.":[196],"method":[198],"F-scores":[200],"over":[202],"0.89":[203],"0.87":[205],"gazee":[207],"eye":[209],"contact":[210],"recognition,":[211],"respectively,":[212],"comparison":[214],"with":[215],"human":[216],"annotation.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
