{"id":"https://openalex.org/W4308222758","doi":"https://doi.org/10.1145/3536221.3558060","title":"The IVI Lab entry to the GENEA Challenge 2022 \u2013 A Tacotron2 Based Method for Co-Speech Gesture Generation With Locality-Constraint Attention Mechanism","display_name":"The IVI Lab entry to the GENEA Challenge 2022 \u2013 A Tacotron2 Based Method for Co-Speech Gesture Generation With Locality-Constraint Attention Mechanism","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4308222758","doi":"https://doi.org/10.1145/3536221.3558060"},"language":"en","primary_location":{"id":"doi:10.1145/3536221.3558060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3558060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558060","source":null,"license":null,"license_id":null,"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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558060","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068325479","display_name":"Che\u2010Jui Chang","orcid":"https://orcid.org/0000-0001-7935-8723"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Che-Jui Chang","raw_affiliation_strings":["Department of Computer Science, Rutgers, The State University of New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0001-7935-8723","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers, The State University of New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013814324","display_name":"Sen Zhang","orcid":"https://orcid.org/0000-0002-8445-4848"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Zhang","raw_affiliation_strings":["Department of Computer Science, Rutgers, The State University of New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0002-8445-4848","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers, The State University of New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069589954","display_name":"Mubbasir Kapadia","orcid":"https://orcid.org/0000-0002-3501-0028"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubbasir Kapadia","raw_affiliation_strings":["Department of Computer Science, Rutgers, The State University of New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0002-3501-0028","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers, The State University of New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9043635725975037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.703818678855896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6347619891166687},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6258604526519775},{"id":"https://openalex.org/keywords/jerk","display_name":"Jerk","score":0.6146752834320068},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5970041155815125},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5768327713012695},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.541641116142273},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5323683619499207},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4704750180244446},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.453448086977005},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.45227178931236267},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.42519354820251465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3279232084751129},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12111324071884155}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9043635725975037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703818678855896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6347619891166687},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6258604526519775},{"id":"https://openalex.org/C181605269","wikidata":"https://www.wikidata.org/wiki/Q497332","display_name":"Jerk","level":3,"score":0.6146752834320068},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5970041155815125},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5768327713012695},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.541641116142273},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5323683619499207},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4704750180244446},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.453448086977005},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.45227178931236267},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.42519354820251465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3279232084751129},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12111324071884155},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3536221.3558060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3558060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558060","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3536221.3558060","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3558060","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3558060","source":null,"license":null,"license_id":null,"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":[],"awards":[{"id":"https://openalex.org/G1209742835","display_name":null,"funder_award_id":"IIS-1703883","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3621817804","display_name":"CHS: Medium: Data Driven Biomechanically Accurate Modeling of Human Gait on Unconstrained Terrain","funder_award_id":"1703883","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3869910071","display_name":null,"funder_award_id":"EAGER-2122119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G499496167","display_name":null,"funder_award_id":"IIS-1703883, IIS-1955404, IIS-1955365, RETTL-2119265, and EAGER-2122119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6979405372","display_name":"EAGER: SAI: Cognitive Models of Human Social Wayfinding for the Redesign of Public Spaces","funder_award_id":"2122119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7157213963","display_name":null,"funder_award_id":"22STESE00001 01 01","funder_id":"https://openalex.org/F4320306110","funder_display_name":"U.S. Department of Homeland Security"},{"id":"https://openalex.org/G7338372148","display_name":"Collaborative Research: RI: Medium: Learning Joint Crowd-Space Embeddings for Cross-Modal Crowd Behavior Prediction","funder_award_id":"1955404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8400860804","display_name":null,"funder_award_id":"IIS-1955404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8492113617","display_name":"The Role of Agency and Interactivity in Embodied Conversational Agents to Support Teacher Training in High Poverty Schools","funder_award_id":"2119265","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8816859997","display_name":"Collaborative Research: RI: Medium: Learning Joint Crowd-Space Embeddings for Cross-Modal Crowd Behavior Prediction","funder_award_id":"1955365","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"},{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308222758.pdf","grobid_xml":"https://content.openalex.org/works/W4308222758.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1977259876","https://openalex.org/W2191779130","https://openalex.org/W2884225676","https://openalex.org/W2962795401","https://openalex.org/W2964243274","https://openalex.org/W2967443589","https://openalex.org/W2973142754","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3009385801","https://openalex.org/W3083173864","https://openalex.org/W3089400186","https://openalex.org/W3091094344","https://openalex.org/W3093973228","https://openalex.org/W3099402851","https://openalex.org/W3118288752","https://openalex.org/W3125775899","https://openalex.org/W3188493377","https://openalex.org/W3198131199","https://openalex.org/W3212693919","https://openalex.org/W4230429791","https://openalex.org/W4292945985"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W4312416068","https://openalex.org/W3147379364","https://openalex.org/W2010878661","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":[3,8,14,32,36,40,47,53,57,60,81,90,105,136,147],"IVI":[4],"Lab":[5],"entry":[6,103],"to":[7,55,121,146],"GENEA":[9,69],"Challenge":[10,70],"2022.":[11],"We":[12,38,115],"formulate":[13],"gesture":[15],"generation":[16],"problem":[17],"as":[18,29,35,43],"a":[19],"sequence-to-sequence":[20],"conversion":[21],"task":[22],"with":[23,46,128],"text,":[24],"audio,":[25],"and":[26,31,78,84,92,126],"speaker":[27],"identity":[28],"inputs":[30],"body":[33,83,86],"motion":[34,124,137],"output.":[37],"use":[39],"Tacotron2":[41],"architecture":[42],"our":[44,74,101,123,140],"backbone":[45],"locality-constraint":[48],"attention":[49],"mechanism":[50],"that":[51,73,135],"guides":[52],"decoder":[54],"learn":[56],"dependencies":[58],"from":[59],"neighboring":[61],"latent":[62],"features.":[63],"The":[64,132],"collective":[65],"evaluation":[66,120],"released":[67],"by":[68],"2022":[71],"indicates":[72,134],"two":[75,97,129],"entries":[76],"(FSH":[77],"USK)":[79],"for":[80],"full":[82],"upper":[85],"tracks":[87],"statistically":[88],"outperform":[89],"audio-driven":[91],"text-driven":[93],"baselines":[94],"on":[95],"both":[96],"subjective":[98],"metrics.":[99],"Remarkably,":[100],"full-body":[102],"receives":[104],"highest":[106],"speech":[107],"appropriateness":[108],"(60.5%":[109],"matched)":[110],"among":[111],"all":[112],"submitted":[113],"entries.":[114],"also":[116],"conduct":[117],"an":[118],"objective":[119],"compare":[122],"acceleration":[125],"jerk":[127],"autoregressive":[130],"baselines.":[131],"result":[133],"distribution":[138,148],"of":[139,149],"generated":[141],"gestures":[142],"is":[143],"much":[144],"closer":[145],"natural":[150],"gestures.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}