{"id":"https://openalex.org/W4387423988","doi":"https://doi.org/10.1145/3577190.3616115","title":"FEIN-Z: Autoregressive Behavior Cloning for Speech-Driven Gesture Generation","display_name":"FEIN-Z: Autoregressive Behavior Cloning for Speech-Driven Gesture Generation","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4387423988","doi":"https://doi.org/10.1145/3577190.3616115"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3616115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3616115","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/A5093021319","display_name":"Leon Harz","orcid":"https://orcid.org/0009-0001-4853-1500"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Leon Harz","raw_affiliation_strings":["Bielefeld University, Germany"],"raw_orcid":"https://orcid.org/0009-0001-4853-1500","affiliations":[{"raw_affiliation_string":"Bielefeld University, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081855415","display_name":"Hendric Vo\u00df","orcid":"https://orcid.org/0009-0003-3646-7702"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hendric Vo\u00df","raw_affiliation_strings":["Social Cognitive Systems - CITEC, Bielefeld University, Germany"],"raw_orcid":"https://orcid.org/0009-0003-3646-7702","affiliations":[{"raw_affiliation_string":"Social Cognitive Systems - CITEC, Bielefeld University, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043486945","display_name":"Stefan Kopp","orcid":"https://orcid.org/0000-0002-4047-9277"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Kopp","raw_affiliation_strings":["Social Cognitive Systems - CITEC, Bielefeld University, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4047-9277","affiliations":[{"raw_affiliation_string":"Social Cognitive Systems - CITEC, Bielefeld University, Germany","institution_ids":["https://openalex.org/I20121455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093021319"],"corresponding_institution_ids":["https://openalex.org/I20121455"],"apc_list":null,"apc_paid":null,"fwci":0.1217,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34395973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"763","last_page":"771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T12290","display_name":"Human Motion and Animation","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8625566959381104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7415376901626587},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5229732990264893},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.49956655502319336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49024540185928345},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4837956130504608},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.44159847497940063},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4236398935317993},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.41890931129455566},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.41704633831977844},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41148704290390015},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.22685202956199646},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09497350454330444}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8625566959381104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415376901626587},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5229732990264893},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.49956655502319336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49024540185928345},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4837956130504608},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.44159847497940063},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4236398935317993},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.41890931129455566},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41704633831977844},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41148704290390015},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.22685202956199646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09497350454330444},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3577190.3616115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3616115","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"},{"id":"pmh:oai:pub.uni-bielefeld.de:2983419","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2983419","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:pub.uni-bielefeld.de:2984549","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2984549","pdf_url":null,"source":{"id":"https://openalex.org/S4306401670","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1208039178","https://openalex.org/W1974604838","https://openalex.org/W1977259876","https://openalex.org/W1991366868","https://openalex.org/W2007337857","https://openalex.org/W2024536104","https://openalex.org/W2058988816","https://openalex.org/W2064675550","https://openalex.org/W2111902182","https://openalex.org/W2115096495","https://openalex.org/W2161870044","https://openalex.org/W2293741035","https://openalex.org/W2493916176","https://openalex.org/W2611706523","https://openalex.org/W2760103357","https://openalex.org/W2901872500","https://openalex.org/W2908510526","https://openalex.org/W2910814616","https://openalex.org/W2945629925","https://openalex.org/W2950635152","https://openalex.org/W2951157474","https://openalex.org/W2962795401","https://openalex.org/W2981802563","https://openalex.org/W2986302981","https://openalex.org/W3009385801","https://openalex.org/W3048577018","https://openalex.org/W3083173864","https://openalex.org/W3093973228","https://openalex.org/W3094502228","https://openalex.org/W3098994456","https://openalex.org/W3107914916","https://openalex.org/W3115266783","https://openalex.org/W3125775899","https://openalex.org/W3170104202","https://openalex.org/W3207529040","https://openalex.org/W3210580323","https://openalex.org/W4287706271","https://openalex.org/W4290662212","https://openalex.org/W4292945985","https://openalex.org/W4293352083","https://openalex.org/W4308173557","https://openalex.org/W4308222520","https://openalex.org/W4308222530","https://openalex.org/W4308222684","https://openalex.org/W4308222716","https://openalex.org/W4308222721","https://openalex.org/W4308222758","https://openalex.org/W4322718191","https://openalex.org/W4364377334","https://openalex.org/W4387421378","https://openalex.org/W4388660746"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4220733532","https://openalex.org/W3016124757","https://openalex.org/W3034520363"],"abstract_inverted_index":{"Human":[0],"communication":[1],"relies":[2],"on":[3,67,89],"multiple":[4],"modalities":[5],"such":[6,135],"as":[7,136],"verbal":[8,53],"expressions,":[9],"facial":[10],"cues,":[11],"and":[12,20,45,81,98,108,120,145],"bodily":[13],"gestures.":[14],"Developing":[15],"computational":[16],"approaches":[17],"to":[18,41,56,84],"process":[19],"generate":[21],"these":[22],"multimodal":[23],"signals":[24],"is":[25,34],"critical":[26],"for":[27,133],"seamless":[28],"human-agent":[29],"interaction.":[30],"A":[31],"particular":[32],"challenge":[33],"the":[35,42,90,105,113,126],"generation":[36],"of":[37,47],"co-speech":[38,85],"gestures":[39,48],"due":[40],"large":[43],"variability":[44],"number":[46],"that":[49,74],"can":[50],"accompany":[51],"a":[52,57,68],"utterance,":[54],"leading":[55],"one-to-many":[58],"mapping":[59],"problem.":[60],"This":[61],"paper":[62],"presents":[63],"an":[64],"approach":[65],"based":[66],"Feature":[69],"Extraction":[70],"Infusion":[71],"Network":[72],"(FEIN-Z)":[73],"adopts":[75],"insights":[76],"from":[77],"robot":[78],"imitation":[79],"learning":[80],"applies":[82],"them":[83],"gesture":[86],"generation.":[87],"Building":[88],"BC-Z":[91],"architecture,":[92],"our":[93],"framework":[94],"combines":[95],"transformer":[96],"architectures":[97],"Wasserstein":[99],"generative":[100],"adversarial":[101],"networks.":[102],"We":[103,129],"describe":[104],"FEIN-Z":[106],"methodology":[107],"evaluation":[109],"results":[110,119],"obtained":[111],"within":[112],"GENEA":[114,127],"Challenge":[115],"2023,":[116],"demonstrating":[117],"good":[118],"significant":[121],"improvements":[122],"in":[123],"human-likeness":[124],"over":[125],"baseline.":[128],"discuss":[130],"potential":[131],"areas":[132],"improvement,":[134],"refining":[137],"input":[138],"segmentation,":[139],"employing":[140],"more":[141],"fine-grained":[142],"control":[143],"networks,":[144],"exploring":[146],"alternative":[147],"inference":[148],"methods.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
