{"id":"https://openalex.org/W4403704329","doi":"https://doi.org/10.1145/3678957.3685707","title":"Learning Co-Speech Gesture Representations in Dialogue through Contrastive Learning: An Intrinsic Evaluation","display_name":"Learning Co-Speech Gesture Representations in Dialogue through Contrastive Learning: An Intrinsic Evaluation","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403704329","doi":"https://doi.org/10.1145/3678957.3685707"},"language":"en","primary_location":{"id":"doi:10.1145/3678957.3685707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678957.3685707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.10535","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046627420","display_name":"Esam Ghaleb","orcid":"https://orcid.org/0000-0002-0603-9817"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Esam Ghaleb","raw_affiliation_strings":["Institute for Logic, Language and Computation (ILLC), University of Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0603-9817","affiliations":[{"raw_affiliation_string":"Institute for Logic, Language and Computation (ILLC), University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086064165","display_name":"Bulat Khaertdinov","orcid":"https://orcid.org/0000-0003-1651-0657"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bulat Khaertdinov","raw_affiliation_strings":["Department of Advanced Computing Sciences, Maastricht University, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1651-0657","affiliations":[{"raw_affiliation_string":"Department of Advanced Computing Sciences, Maastricht University, Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051882032","display_name":"Wim Pouw","orcid":"https://orcid.org/0000-0003-2729-6502"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wim Pouw","raw_affiliation_strings":["Radboud University, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2729-6502","affiliations":[{"raw_affiliation_string":"Radboud University, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018407432","display_name":"Marlou Rasenberg","orcid":"https://orcid.org/0000-0003-1812-6907"},"institutions":[{"id":"https://openalex.org/I4210158762","display_name":"Meertens Institute","ror":"https://ror.org/05kaxyq51","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210158762"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marlou Rasenberg","raw_affiliation_strings":["Meertens Institute, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1812-6907","affiliations":[{"raw_affiliation_string":"Meertens Institute, Netherlands","institution_ids":["https://openalex.org/I4210158762"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003283632","display_name":"Judith Holler","orcid":"https://orcid.org/0000-0003-0671-6651"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Judith Holler","raw_affiliation_strings":["Radboud University, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0671-6651","affiliations":[{"raw_affiliation_string":"Radboud University, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031001554","display_name":"Asl\u0131 \u00d6zy\u00fcrek","orcid":"https://orcid.org/0000-0003-4914-2643"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Asli Ozyurek","raw_affiliation_strings":["Radboud University, Donders Institute, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4914-2643","affiliations":[{"raw_affiliation_string":"Radboud University, Donders Institute, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058407281","display_name":"Ronald T. Fern\u00e1ndez","orcid":"https://orcid.org/0000-0001-5540-5943"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Raquel Fernandez","raw_affiliation_strings":["Institute for Logic, Language and Computationa, University of Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-5540-5943","affiliations":[{"raw_affiliation_string":"Institute for Logic, Language and Computationa, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3635,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53868152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"274","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"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":0.9998000264167786,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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":0.9836999773979187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.9545015096664429},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7084212303161621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5775653719902039},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5325718522071838},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5047644376754761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41132792830467224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3877919912338257},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22370368242263794}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9545015096664429},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7084212303161621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5775653719902039},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5325718522071838},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5047644376754761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41132792830467224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3877919912338257},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22370368242263794},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3678957.3685707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3678957.3685707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Multimodel Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:publications/2173dbfa-1003-4326-8338-3e6a8bc9cc2a","is_oa":false,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/2173dbfa-1003-4326-8338-3e6a8bc9cc2a","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2409.10535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.10535","pdf_url":"https://arxiv.org/pdf/2409.10535","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire/5e7c8a8d-71b5-4502-a7c3-59c9ec5f4ed8","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/learning-cospeech-gesture-representations-in-dialogue-through-contrastive-learning-an-intrinsic-evaluation(5e7c8a8d-71b5-4502-a7c3-59c9ec5f4ed8).html","pdf_url":"https://pure.uva.nl/ws/files/273964825/3678957.3685707.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_3644943","is_oa":true,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0011-017E-F","pdf_url":"https://hdl.handle.net/21.11116/0000-0011-0180-A","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 26th International Conference on Multimodal Interaction (ICMI 2024)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.10535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.10535","pdf_url":"https://arxiv.org/pdf/2409.10535","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2084304408","display_name":null,"funder_award_id":"024.001.006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403704329.pdf","grobid_xml":"https://content.openalex.org/works/W4403704329.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1498341987","https://openalex.org/W1977995219","https://openalex.org/W2029364672","https://openalex.org/W2167930377","https://openalex.org/W2495931130","https://openalex.org/W2605717780","https://openalex.org/W2767624150","https://openalex.org/W2890144450","https://openalex.org/W2922298118","https://openalex.org/W2963076818","https://openalex.org/W2964109882","https://openalex.org/W2964204621","https://openalex.org/W2990165697","https://openalex.org/W3005254336","https://openalex.org/W3006913151","https://openalex.org/W3035524453","https://openalex.org/W3083173864","https://openalex.org/W3099073275","https://openalex.org/W3114632476","https://openalex.org/W3125775899","https://openalex.org/W3127443383","https://openalex.org/W3135367836","https://openalex.org/W3160747790","https://openalex.org/W3169413442","https://openalex.org/W3170177690","https://openalex.org/W3174109486","https://openalex.org/W3184215204","https://openalex.org/W3188493377","https://openalex.org/W3191974319","https://openalex.org/W3197642003","https://openalex.org/W3202070718","https://openalex.org/W3205106480","https://openalex.org/W3209059054","https://openalex.org/W3210580323","https://openalex.org/W4200634815","https://openalex.org/W4213052788","https://openalex.org/W4221109102","https://openalex.org/W4225726571","https://openalex.org/W4281393069","https://openalex.org/W4308192751","https://openalex.org/W4312923619","https://openalex.org/W4319862479","https://openalex.org/W4364377334","https://openalex.org/W4386071707","https://openalex.org/W4393148235","https://openalex.org/W4394625639"],"related_works":["https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650"],"abstract_inverted_index":{"In":[0],"face-to-face":[1,92],"dialogues,":[2],"the":[3,17,22,106,125,133,150,153,163,176,184,205],"form-meaning":[4],"relationship":[5,46],"of":[6,25,105,127,165,178],"co-speech":[7,30],"gestures":[8,18,40,179],"varies":[9],"depending":[10],"on":[11],"contextual":[12],"factors":[13,28],"such":[14,209],"as":[15],"what":[16],"refer":[19],"to":[20,60,80,123,162,207],"and":[21,45,66,77,147],"individual":[23],"characteristics":[24],"speakers.":[26],"These":[27],"make":[29],"gesture":[31,62,82,114,130,145,201,213],"representation":[32],"learning":[33,58,194,200],"challenging.":[34],"How":[35],"can":[36,180],"we":[37,89,117],"learn":[38,61],"meaningful":[39],"representations":[41,63,83,108,155,210],"considering":[42],"gestures\u2019":[43],"variability":[44],"with":[47,96,111,143,158],"speech?":[48],"This":[49],"paper":[50],"tackles":[51],"this":[52,188],"challenge":[53],"by":[54],"employing":[55],"self-supervised":[56],"contrastive":[57,193],"techniques":[59],"from":[64,132,183],"skeletal":[65],"speech":[67],"information.":[68],"We":[69,100],"propose":[70],"an":[71],"approach":[72,198],"that":[73,149,172,191],"includes":[74],"both":[75],"unimodal":[76],"multimodal":[78,192],"pre-training":[79],"ground":[81],"in":[84,211],"co-occurring":[85],"speech.":[86],"For":[87],"training,":[88],"utilize":[90],"a":[91,119,139,196],"dialogue":[93,166],"dataset":[94],"rich":[95],"representational":[97],"iconic":[98],"gestures.":[99],"conduct":[101],"thorough":[102],"intrinsic":[103],"evaluations":[104],"learned":[107,134,154],"through":[109],"comparison":[110],"human-annotated":[112,144],"pairwise":[113],"similarity.":[115],"Moreover,":[116,168],"perform":[118],"diagnostic":[120],"probing":[121],"analysis":[122,214],"assess":[124],"possibility":[126],"recovering":[128],"interpretable":[129],"features":[131,174],"representations.":[135,186],"Our":[136],"results":[137],"show":[138],"significant":[140],"positive":[141],"correlation":[142],"similarity":[146,151],"reveal":[148],"between":[152],"is":[156,195],"consistent":[157],"well-motivated":[159],"patterns":[160],"related":[161],"dynamics":[164],"interaction.":[167],"our":[169],"findings":[170],"demonstrate":[171],"several":[173],"concerning":[175],"form":[177],"be":[181],"recovered":[182],"latent":[185],"Overall,":[187],"study":[189],"shows":[190],"promising":[197],"for":[199],"representations,":[202],"which":[203],"opens":[204],"door":[206],"using":[208],"larger-scale":[212],"studies.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-10-24T00:00:00"}