{"id":"https://openalex.org/W7118000600","doi":"https://doi.org/10.1145/3765766.3765771","title":"Multimodal Classification of Co-speech Gesture Pragmatic Function in Storytelling","display_name":"Multimodal Classification of Co-speech Gesture Pragmatic Function in Storytelling","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7118000600","doi":"https://doi.org/10.1145/3765766.3765771"},"language":null,"primary_location":{"id":"doi:10.1145/3765766.3765771","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765771","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3765766.3765771","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121829530","display_name":"Jinqian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jinqian Zhang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0002-6339-7124","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061418266","display_name":"Sixia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sixia Li","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0009-0007-3985-6892","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005680805","display_name":"Candy Olivia Mawalim","orcid":"https://orcid.org/0000-0001-9853-8893"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Candy Olivia Mawalim","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9853-8893","affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121763687","display_name":"Shogo Okada","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Okada","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9260-0403","affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121829530"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64552316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.2913999855518341,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.2913999855518341,"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/T12031","display_name":"Speech and dialogue systems","score":0.14990000426769257,"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/T11431","display_name":"Action Observation and Synchronization","score":0.12389999628067017,"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/gesture","display_name":"Gesture","score":0.8572999835014343},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7940000295639038},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5078999996185303},{"id":"https://openalex.org/keywords/storytelling","display_name":"Storytelling","score":0.37630000710487366},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3149000108242035}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8572999835014343},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7940000295639038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042999863624573},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C2776538412","wikidata":"https://www.wikidata.org/wiki/Q989963","display_name":"Storytelling","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3666999936103821},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C30539005","wikidata":"https://www.wikidata.org/wiki/Q1066689","display_name":"Human communication","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765766.3765771","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765771","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:10.1145/3765766.3765771","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765766.3765771","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7749302387237549}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1493636870","https://openalex.org/W1498883201","https://openalex.org/W1935857547","https://openalex.org/W1968600824","https://openalex.org/W1985827989","https://openalex.org/W1990526545","https://openalex.org/W2057738678","https://openalex.org/W2059701405","https://openalex.org/W2074772342","https://openalex.org/W2091425152","https://openalex.org/W2148154194","https://openalex.org/W2170085298","https://openalex.org/W2191779130","https://openalex.org/W2255466643","https://openalex.org/W2395639500","https://openalex.org/W2604166870","https://openalex.org/W2606032136","https://openalex.org/W2619383789","https://openalex.org/W2730314078","https://openalex.org/W2736431578","https://openalex.org/W2922127468","https://openalex.org/W2947199483","https://openalex.org/W2963351448","https://openalex.org/W3047269745","https://openalex.org/W3203381367","https://openalex.org/W3203655597","https://openalex.org/W3205445153","https://openalex.org/W3207267043","https://openalex.org/W4229082061","https://openalex.org/W4364377334","https://openalex.org/W4367297395","https://openalex.org/W4387421761","https://openalex.org/W4390094952","https://openalex.org/W4404284944","https://openalex.org/W4405813023"],"related_works":[],"abstract_inverted_index":{"Gestures,":[0],"as":[1],"essential":[2],"co-speech":[3,65],"behaviors":[4],"in":[5,67,179],"human":[6],"communication,":[7],"carry":[8],"rich":[9],"pragmatic":[10,53,76],"functions.":[11],"Accurately":[12],"recognizing":[13],"these":[14],"functions":[15,31],"could":[16],"enhance":[17,181],"an":[18],"agent\u2019s":[19],"ability":[20],"to":[21,49,113],"understand":[22],"communicative":[23],"behavior.":[24],"In":[25],"spontaneous":[26],"storytelling":[27],"scenarios\u2014unlike":[28],"lab-controlled":[29],"settings\u2014gesture":[30],"exhibit":[32],"high":[33],"variability":[34],"and":[35,61,93,109,117,132,146,175],"are":[36,104,170],"strongly":[37],"influenced":[38],"by":[39,149],"individual":[40],"speaker":[41],"differences,":[42],"making":[43],"it":[44],"difficult":[45],"for":[46,162,172],"unimodal":[47],"systems":[48],"reliably":[50],"capture":[51,114],"their":[52],"intent.":[54],"To":[55],"address":[56],"this":[57],"challenge,":[58],"we":[59],"collected":[60],"annotated":[62],"naturally":[63],"occurring":[64],"gestures":[66],"narrative":[68],"dialogues,":[69],"assigning":[70],"each":[71],"gesture":[72,166],"one":[73],"of":[74,137,165],"six":[75],"function":[77],"labels.":[78],"We":[79],"further":[80],"propose":[81],"a":[82,110,133],"multimodal":[83],"sequential":[84],"classification":[85,142],"model":[86],"that":[87,125,154],"encodes":[88],"skeletal":[89,155],"motion,":[90],"acoustic":[91,168],"prosody,":[92],"facial":[94,176],"dynamics":[95],"using":[96],"separate":[97],"bidirectional":[98],"LSTM":[99],"networks.":[100],"These":[101],"modality-specific":[102],"encodings":[103],"fused":[105],"via":[106,186],"cross-modal":[107],"attention":[108],"gated":[111],"mechanism":[112],"temporal":[115],"dependencies":[116],"complementary":[118],"information":[119],"across":[120],"modalities.":[121],"Experimental":[122],"results":[123],"demonstrate":[124],"our":[126],"tri-modal":[127],"system":[128],"achieves":[129],"62.5%":[130],"accuracy":[131],"weighted":[134],"F1":[135],"score":[136],"0.62":[138],"on":[139],"the":[140,158,163],"six-way":[141],"task,":[143],"outperforming":[144],"uni-modal":[145],"bi-modal":[147],"baselines":[148],"3\u201311%.":[150],"Ablation":[151],"analysis":[152],"reveals":[153],"features":[156,169],"provide":[157],"most":[159],"discriminative":[160],"power":[161],"majority":[164],"functions,":[167],"critical":[171],"specific":[173],"categories,":[174],"features\u2014though":[177],"weak":[178],"isolation\u2014substantially":[180],"overall":[182],"performance":[183],"when":[184],"integrated":[185],"attention.":[187]},"counts_by_year":[],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2026-01-02T00:00:00"}
