{"id":"https://openalex.org/W4293352083","doi":"https://doi.org/10.1145/3536221.3558066","title":"The ReprGesture entry to the GENEA Challenge 2022","display_name":"The ReprGesture entry to the GENEA Challenge 2022","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4293352083","doi":"https://doi.org/10.1145/3536221.3558066"},"language":"en","primary_location":{"id":"doi:10.1145/3536221.3558066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3558066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558066","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 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112200211","display_name":"Sicheng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0001-8533-0524","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China and The Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China and The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780135","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0002-1427-3507"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103832112","display_name":"Mengchen Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengchen Zhao","raw_affiliation_strings":["Huawei Noah's Ark Lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025480447","display_name":"Jiuxin Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuxin Lin","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849127","display_name":"Liyang Chen","orcid":"https://orcid.org/0000-0001-6985-8281"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyang Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036821828","display_name":"Weihong Bao","orcid":"https://orcid.org/0009-0008-4696-854X"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihong Bao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"758","last_page":"763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","score":0.9925000071525574,"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":0.8196775913238525},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7854700088500977},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7677819728851318},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5990577936172485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5808202028274536},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45741528272628784},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4502045214176178},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.43369990587234497},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34293118119239807}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8196775913238525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854700088500977},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7677819728851318},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5990577936172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5808202028274536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45741528272628784},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4502045214176178},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.43369990587234497},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34293118119239807}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3536221.3558066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3558066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558066","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 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.12133","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.12133","pdf_url":"https://arxiv.org/pdf/2208.12133","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3536221.3558066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3558066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558066","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 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329174","display_name":"Shenzhen Municipal Science and Technology Innovation Council","ror":"https://ror.org/017n8df75"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293352083.pdf","grobid_xml":"https://content.openalex.org/works/W4293352083.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2922298118","https://openalex.org/W2946165673","https://openalex.org/W2967443589","https://openalex.org/W3009385801","https://openalex.org/W3042815677","https://openalex.org/W3083173864","https://openalex.org/W3093051361","https://openalex.org/W3093647117","https://openalex.org/W3099073275","https://openalex.org/W3125087480","https://openalex.org/W3125775899","https://openalex.org/W3132298525","https://openalex.org/W3133090439","https://openalex.org/W3153551559","https://openalex.org/W3207098744","https://openalex.org/W4230429791","https://openalex.org/W4292945985","https://openalex.org/W4312674262"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,24,33,90,122,125],"ReprGesture":[4],"entry":[5],"to":[6,31,77,121],"Generation":[8],"and":[9,27,65,67,82,88,101,118,131],"Evaluation":[10],"of":[11,35,92],"Non-verbal":[12],"Behaviour":[13],"for":[14,59,63,71],"Embodied":[15],"Agents":[16],"(GENEA)":[17],"challenge":[18,22],"2022.":[19],"The":[20,109],"GENEA":[21],"provides":[23],"processed":[25],"datasets":[26],"performs":[28],"crowdsourced":[29],"evaluations":[30],"compare":[32],"performance":[34],"different":[36],"gesture":[37,47,110],"generation":[38,48],"systems.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"explore":[44],"an":[45],"automatic":[46],"system":[49],"based":[50,98],"on":[51],"multimodal":[52],"representation":[53],"learning.":[54],"We":[55],"use":[56],"WavLM":[57],"features":[58,62,70,119],"audio,":[60],"FastText":[61],"text":[64],"position":[66],"rotation":[68],"matrix":[69],"gesture.":[72],"Each":[73],"modality":[74,102],"is":[75],"projected":[76],"two":[78],"distinct":[79],"subspaces:":[80],"modality-invariant":[81],"modality-specific.":[83],"To":[84],"learn":[85],"inter-modality-invariant":[86],"commonalities":[87],"capture":[89],"characters":[91],"modality-specific":[93],"representations,":[94],"gradient":[95],"reversal":[96],"layer":[97],"adversarial":[99],"classifier":[100],"reconstruction":[103],"decoders":[104],"are":[105,133],"used":[106],"during":[107],"training.":[108],"decoder":[111],"generates":[112],"proper":[113],"gestures":[114],"using":[115],"all":[116],"representations":[117],"related":[120],"rhythm":[123],"in":[124],"audio.":[126],"Our":[127],"code,":[128],"pre-trained":[129],"models":[130],"demo":[132],"available":[134],"at":[135],"https://github.com/YoungSeng/ReprGesture.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}