{"id":"https://openalex.org/W4387421683","doi":"https://doi.org/10.1145/3577190.3614139","title":"Multimodal Turn Analysis and Prediction for Multi-party Conversations","display_name":"Multimodal Turn Analysis and Prediction for Multi-party Conversations","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4387421683","doi":"https://doi.org/10.1145/3577190.3614139"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3614139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614139","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5005674450","display_name":"Meng-Chen Lee","orcid":"https://orcid.org/0009-0002-9726-1153"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Meng-Chen Lee","raw_affiliation_strings":["Department of Computer Science, University of Houston, United States"],"raw_orcid":"https://orcid.org/0009-0002-9726-1153","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, United States","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002935215","display_name":"May Trinh","orcid":"https://orcid.org/0000-0001-6220-6133"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mai Trinh","raw_affiliation_strings":["Department of Computer Science, University of Houston, United States"],"raw_orcid":"https://orcid.org/0000-0001-6220-6133","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, United States","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026683388","display_name":"Zhigang Deng","orcid":"https://orcid.org/0000-0002-0452-8676"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhigang Deng","raw_affiliation_strings":["Department of Computer Science, University of Houston, United States"],"raw_orcid":"https://orcid.org/0000-0002-0452-8676","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, United States","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005674450"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.9692,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75721649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9965999722480774,"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":0.6259379386901855},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.5913275480270386},{"id":"https://openalex.org/keywords/turn","display_name":"Turn (biochemistry)","score":0.5379872918128967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33714258670806885},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.1764947772026062},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.13981318473815918},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0886077880859375},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08475905656814575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6259379386901855},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.5913275480270386},{"id":"https://openalex.org/C85641259","wikidata":"https://www.wikidata.org/wiki/Q290042","display_name":"Turn (biochemistry)","level":2,"score":0.5379872918128967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33714258670806885},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.1764947772026062},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.13981318473815918},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0886077880859375},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08475905656814575},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577190.3614139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614139","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5414807051","display_name":null,"funder_award_id":"IIS 2005430","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":31,"referenced_works":["https://openalex.org/W58692019","https://openalex.org/W1526675628","https://openalex.org/W1566669007","https://openalex.org/W1964725106","https://openalex.org/W1981611667","https://openalex.org/W1985479696","https://openalex.org/W2015111784","https://openalex.org/W2100356893","https://openalex.org/W2105594594","https://openalex.org/W2116971293","https://openalex.org/W2116985048","https://openalex.org/W2139659117","https://openalex.org/W2141666434","https://openalex.org/W2147743504","https://openalex.org/W2166637769","https://openalex.org/W2260472133","https://openalex.org/W2293392332","https://openalex.org/W2401047175","https://openalex.org/W2486828091","https://openalex.org/W2591348521","https://openalex.org/W2610786808","https://openalex.org/W2807877245","https://openalex.org/W2894861209","https://openalex.org/W2896753156","https://openalex.org/W2903611517","https://openalex.org/W2963093689","https://openalex.org/W2965465515","https://openalex.org/W2980823180","https://openalex.org/W3023876185","https://openalex.org/W4283268092","https://openalex.org/W4307680525"],"related_works":["https://openalex.org/W2900127165","https://openalex.org/W320957374","https://openalex.org/W2379107843","https://openalex.org/W3120641923","https://openalex.org/W2909654650","https://openalex.org/W3161619631","https://openalex.org/W4242512034","https://openalex.org/W3003178987","https://openalex.org/W4400912116","https://openalex.org/W4376475259"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,21,29,64,106,150],"computational":[4,66,108],"study":[5],"to":[6,27,68],"analyze":[7],"and":[8,13,78,91,117,126,129],"predict":[9,69],"turns":[10,71,160],"(i.e.,":[11],"turn-taking":[12,127],"turn-keeping)":[14],"in":[15,39,161],"multiparty":[16,162],"conversations.":[17,163],"Specifically,":[18],"we":[19,62,104],"use":[20],"high-fidelity":[22],"hybrid":[23],"data":[24],"acquisition":[25],"system":[26],"capture":[28],"large-scale":[30],"set":[31],"of":[32,37,94,115,142],"multi-modal":[33],"natural":[34],"conversational":[35,132],"behaviors":[36,157],"interlocutors":[38],"three-party":[40],"conversations,":[41],"including":[42],"gazes,":[43],"head":[44],"movements,":[45,47],"body":[46],"speech,":[48],"etc.":[49],"Based":[50],"on":[51,73],"the":[52,58,70,74,79,92,140,143],"inter-pausal":[53],"units":[54],"(IPUs)":[55],"extracted":[56],"from":[57],"in-house":[59],"acquired":[60],"dataset,":[61],"propose":[63],"transformer-based":[65],"model":[67,83,96],"based":[72],"interlocutor":[75,144],"states":[76,145],"(speaking/back-channeling/silence)":[77],"gaze":[80,156],"targets.":[81],"Our":[82,134],"can":[84,146],"robustly":[85],"achieve":[86],"more":[87,151],"than":[88,154],"80%":[89],"accuracy,":[90],"generalizability":[93],"our":[95],"was":[97],"extensively":[98],"validated":[99],"through":[100],"cross-group":[101],"experiments.":[102],"Also,":[103],"introduce":[105],"novel":[107],"metric":[109],"called":[110],"\u201crelative":[111],"engagement":[112],"level\"":[113],"(REL)":[114],"IPUs,":[116,128],"further":[118],"validate":[119],"its":[120],"statistical":[121],"significance":[122],"between":[123,130],"turn-keeping":[124],"IPUs":[125],"different":[131],"groups.":[133],"experimental":[135],"results":[136],"also":[137],"found":[138],"that":[139],"patterns":[141],"be":[147],"used":[148],"as":[149],"effective":[152],"cue":[153],"their":[155],"for":[158],"predicting":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}