{"id":"https://openalex.org/W2979154891","doi":"https://doi.org/10.1145/3349537.3351908","title":"An Investigation on the Effectiveness of Multimodal Fusion and Temporal Feature Extraction in Reactive and Spontaneous Behavior Generative RNN Models for Listener Agents","display_name":"An Investigation on the Effectiveness of Multimodal Fusion and Temporal Feature Extraction in Reactive and Spontaneous Behavior Generative RNN Models for Listener Agents","publication_year":2019,"publication_date":"2019-09-25","ids":{"openalex":"https://openalex.org/W2979154891","doi":"https://doi.org/10.1145/3349537.3351908","mag":"2979154891"},"language":"en","primary_location":{"id":"doi:10.1145/3349537.3351908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3349537.3351908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Human-Agent Interaction","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/A5084384514","display_name":"Hung\u2010Hsuan Huang","orcid":"https://orcid.org/0000-0002-0376-3535"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hung-Hsuan Huang","raw_affiliation_strings":["RIKEN & Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN & Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113552011","display_name":"Masato Fukuda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Fukuda","raw_affiliation_strings":["RIKEN, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN, Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108427048","display_name":"Toyoaki Nishida","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toyoaki Nishida","raw_affiliation_strings":["RIKEN & Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN & Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4118,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64960422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7277358770370483},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6394271850585938},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6206948161125183},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5808199644088745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5782046318054199},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.518487811088562},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4320467710494995},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4284262955188751},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34267356991767883},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3260268568992615},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0947321355342865},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.054893434047698975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277358770370483},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6394271850585938},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6206948161125183},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5808199644088745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5782046318054199},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.518487811088562},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4320467710494995},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4284262955188751},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34267356991767883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3260268568992615},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0947321355342865},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.054893434047698975},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.1145/3349537.3351908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3349537.3351908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Human-Agent Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W194972339","https://openalex.org/W1501669607","https://openalex.org/W1521515648","https://openalex.org/W1524725000","https://openalex.org/W1867279877","https://openalex.org/W1921786749","https://openalex.org/W1997225982","https://openalex.org/W2028632271","https://openalex.org/W2064675550","https://openalex.org/W2087392613","https://openalex.org/W2126822690","https://openalex.org/W2135776491","https://openalex.org/W2148338187","https://openalex.org/W2163699396","https://openalex.org/W2165044370","https://openalex.org/W2740440254","https://openalex.org/W2767249564","https://openalex.org/W2895350599","https://openalex.org/W2900508683","https://openalex.org/W2900728424","https://openalex.org/W2901872500","https://openalex.org/W2903578213","https://openalex.org/W2950635152","https://openalex.org/W2951127645","https://openalex.org/W2958536207","https://openalex.org/W3131553854"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W2136054869","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2385132419","https://openalex.org/W2772780115","https://openalex.org/W2114557664"],"abstract_inverted_index":{"Like":[0],"a":[1,4,136],"human":[2],"listener,":[3],"listener":[5],"agent":[6],"reacts":[7],"to":[8],"its":[9],"communicational":[10],"partners'":[11],"non-verbal":[12],"behaviors":[13,38],"such":[14],"as":[15,27,144],"head":[16,111,122],"nods,":[17],"facial":[18,115,126],"expressions,":[19,116,127],"and":[20,29,36,61,85,117,128,160],"voice":[21,129],"tone.":[22,130],"When":[23],"adopting":[24],"these":[25,74],"modalities":[26,164],"inputs":[28],"develop":[30],"the":[31,43,51,77,94,104,120,145],"generative":[32],"model":[33],"of":[34,45,53,58,65,76,81,96,106,139,163,171],"reactive":[35,84],"spontaneous":[37,86],"using":[39],"machine":[40],"learning":[41],"techniques,":[42],"issues":[44,75],"multimodal":[46],"fusion":[47],"emerge.":[48],"That":[49],"is,":[50],"effectiveness":[52],"different":[54],"modalities,":[55,60],"frame-wise":[56,161],"interaction":[57,162],"multiple":[59],"temporal":[62,169],"feature":[63],"extraction":[64],"individual":[66,172],"modalities.":[67,173],"This":[68],"paper":[69],"describes":[70],"our":[71],"investigation":[72],"on":[73,93],"task":[78],"in":[79,103,135],"generating":[80,107],"virtual":[82],"listeners'":[83],"idling":[87],"behaviors.":[88],"The":[89,148],"work":[90],"is":[91,142,154,165],"based":[92],"comparison":[95],"corresponding":[97],"recurrent":[98],"neural":[99],"network":[100],"(RNN)":[101],"configurations":[102],"performance":[105],"listener's":[108],"(the":[109],"agent)":[110],"movements,":[112,123],"gaze":[113,124],"directions,":[114,125],"postures":[118],"from":[119],"speaker's":[121],"A":[131],"data":[132],"corpus":[133],"recorded":[134],"subject":[137],"experiment":[138],"active":[140],"listening":[141],"used":[143],"ground":[146],"truth.":[147],"results":[149],"showed":[150],"that":[151],"video":[152],"information":[153],"more":[155,166],"effective":[156,167],"than":[157,168],"audio":[158],"information,":[159],"characteristics":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}