{"id":"https://openalex.org/W7117971127","doi":"https://doi.org/10.1145/3765766.3765855","title":"A Facial Expression Generation Model for Listening Agents Considering Speaker Engagement in Active Listening Conversation","display_name":"A Facial Expression Generation Model for Listening Agents Considering Speaker Engagement in Active Listening Conversation","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7117971127","doi":"https://doi.org/10.1145/3765766.3765855"},"language":null,"primary_location":{"id":"doi:10.1145/3765766.3765855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765855","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3765766.3765855","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121828661","display_name":"Hide Hosoda","orcid":null},"institutions":[{"id":"https://openalex.org/I3130243125","display_name":"University of Fukuchiyama","ror":"https://ror.org/04w7k2121","country_code":"JP","type":"education","lineage":["https://openalex.org/I3130243125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hide Hosoda","raw_affiliation_strings":["Graduate School of Region-Centric Informatics, The University of Fukuchiyama, Fukuchiyama, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0009-0002-6640-3008","affiliations":[{"raw_affiliation_string":"Graduate School of Region-Centric Informatics, The University of Fukuchiyama, Fukuchiyama, Kyoto, Japan","institution_ids":["https://openalex.org/I3130243125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084384514","display_name":"Hung\u2010Hsuan Huang","orcid":"https://orcid.org/0000-0002-0376-3535"},"institutions":[{"id":"https://openalex.org/I3130243125","display_name":"University of Fukuchiyama","ror":"https://ror.org/04w7k2121","country_code":"JP","type":"education","lineage":["https://openalex.org/I3130243125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hung-Hsuan Huang","raw_affiliation_strings":["Graduate School of Region-Centric Informatics, The University of Fukuchiyama, Fukuchiyama, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0376-3535","affiliations":[{"raw_affiliation_string":"Graduate School of Region-Centric Informatics, The University of Fukuchiyama, Fukuchiyama, Kyoto, Japan","institution_ids":["https://openalex.org/I3130243125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3130243125"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59523052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.6668999791145325,"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":0.6668999791145325,"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/T11448","display_name":"Face recognition and analysis","score":0.20990000665187836,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.05530000105500221,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7626000046730042},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.7451000213623047},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6561999917030334},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6198999881744385},{"id":"https://openalex.org/keywords/facial-expression-recognition","display_name":"Facial expression recognition","score":0.4392000138759613},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4250999987125397},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.396699994802475}],"concepts":[{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7626000046730042},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7451000213623047},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6561999917030334},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6371999979019165},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6198999881744385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.4392000138759613},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3587000072002411},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3208000063896179},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3203999996185303},{"id":"https://openalex.org/C2986659363","wikidata":"https://www.wikidata.org/wiki/Q6646450","display_name":"Listening comprehension","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765766.3765855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765855","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3765766.3765855","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765855","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2087392613","https://openalex.org/W2979154891","https://openalex.org/W4287509562"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3],"facial":[4,56,96],"expression":[5,97],"generation":[6],"model":[7,29],"for":[8],"attentive":[9],"listening":[10],"behavior":[11],"using":[12,81],"conditional":[13],"Generative":[14],"Adversarial":[15],"Networks":[16],"(GAN),":[17],"based":[18],"on":[19],"Skype-based":[20],"conversations":[21],"between":[22],"elderly":[23],"individuals":[24],"and":[25,38,41],"university":[26],"students.":[27],"The":[28,50,77],"takes":[30],"as":[31,63,83,88],"input":[32],"the":[33,46,53,64,93],"speaker\u2019s":[34,47],"non-verbal":[35],"features\u2013facial":[36],"expressions":[37],"head":[39],"pose":[40],"prosodic":[42],"features":[43],"along":[44],"with":[45,71],"engagement":[48,75,82],"state.":[49],"output":[51],"is":[52],"listener":[54],"agent\u2019s":[55],"movements.":[57],"Using":[58],"Frechet":[59],"Motion":[60],"Distance":[61],"(FMD)":[62],"evaluation":[65],"metric,":[66],"we":[67],"compared":[68],"four":[69],"models":[70],"different":[72],"forms":[73],"of":[74,95],"input.":[76],"results":[78],"showed":[79],"that":[80],"five-level":[84],"categorical":[85],"labels":[86],"or":[87],"continuous":[89],"values":[90],"significantly":[91],"improved":[92],"accuracy":[94],"generation.":[98]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-02T00:00:00"}