{"id":"https://openalex.org/W7133332291","doi":"https://doi.org/10.1109/ijcb65343.2025.11411217","title":"Hierarchical Emotion-Guided Masked Transformer for Long-Sequence Co-Speech Gestures with Partial Supervision","display_name":"Hierarchical Emotion-Guided Masked Transformer for Long-Sequence Co-Speech Gestures with Partial Supervision","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7133332291","doi":"https://doi.org/10.1109/ijcb65343.2025.11411217"},"language":null,"primary_location":{"id":"doi:10.1109/ijcb65343.2025.11411217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11411217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","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/A5127976811","display_name":"Hao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426838","display_name":"Jiangtao Li","orcid":"https://orcid.org/0000-0003-2005-472X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtao Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404994","display_name":"Dongze Li","orcid":"https://orcid.org/0009-0009-4567-1506"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongze Li","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079579315","display_name":"Kunbo Zhang","orcid":"https://orcid.org/0000-0002-4826-6831"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunbo Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127890731","display_name":"Zhenan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, MAIS, Institute of Automation","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73553735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4404999911785126,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4404999911785126,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.22519999742507935,"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/T10860","display_name":"Speech and Audio Processing","score":0.08399999886751175,"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":0.8187999725341797},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5669999718666077},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5152999758720398},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.43939998745918274},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.36169999837875366},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.34310001134872437},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8187999725341797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358999848365784},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354999899864197},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5152999758720398},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb65343.2025.11411217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11411217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1534876773","https://openalex.org/W2022214202","https://openalex.org/W2151539117","https://openalex.org/W2603777577","https://openalex.org/W2612744935","https://openalex.org/W2901285216","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2978956737","https://openalex.org/W3013020904","https://openalex.org/W3024902055","https://openalex.org/W3083173864","https://openalex.org/W3096831136","https://openalex.org/W3180400604","https://openalex.org/W3188493377","https://openalex.org/W3194872882","https://openalex.org/W3198131199","https://openalex.org/W3204107037","https://openalex.org/W3204221554","https://openalex.org/W4221142137","https://openalex.org/W4303448003","https://openalex.org/W4310483793","https://openalex.org/W4312388283","https://openalex.org/W4312462635","https://openalex.org/W4312674262","https://openalex.org/W4312719027","https://openalex.org/W4312936899","https://openalex.org/W4313036342","https://openalex.org/W4323240786","https://openalex.org/W4364377334","https://openalex.org/W4377001520","https://openalex.org/W4378220554","https://openalex.org/W4385245566","https://openalex.org/W4385284180","https://openalex.org/W4386076103","https://openalex.org/W4386270206","https://openalex.org/W4388623205","https://openalex.org/W4390871693","https://openalex.org/W4390872470","https://openalex.org/W4390873054","https://openalex.org/W4390874170","https://openalex.org/W4392910552","https://openalex.org/W4396877837","https://openalex.org/W4399206662","https://openalex.org/W4400822426","https://openalex.org/W4402703119","https://openalex.org/W4402704505","https://openalex.org/W4402716435","https://openalex.org/W4402727037","https://openalex.org/W4402727140","https://openalex.org/W4402727590","https://openalex.org/W4402753998","https://openalex.org/W4402951694","https://openalex.org/W4403878062","https://openalex.org/W4404553937","https://openalex.org/W4404879538","https://openalex.org/W4404965941","https://openalex.org/W4405003361","https://openalex.org/W4409263278","https://openalex.org/W4413155897","https://openalex.org/W4413292112"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,50,61,67,86,131,148],"method":[4,158],"for":[5],"co-speech":[6,164],"gesture":[7,44,165],"generation":[8],"that":[9,55,91],"produces":[10],"natural,":[11],"emotionally":[12],"expressive":[13],"body":[14],"movements":[15],"synchronized":[16],"with":[17],"speech.":[18],"Existing":[19],"methods":[20],"typically":[21],"assume":[22],"complete":[23],"motion":[24,172],"supervision":[25],"and":[26,34,77,104,125,144,174],"static":[27],"emotional":[28,94,154],"states,":[29],"limiting":[30],"training":[31],"data":[32,76],"leverage":[33],"impairing":[35],"fine-grained":[36],"emotion":[37,103,119],"transitions,":[38],"ultimately":[39],"leading":[40],"to":[41,114],"incoherent":[42],"long-sequence":[43,163],"generation.":[45],"In":[46],"contrast,":[47],"we":[48],"propose":[49],"Hierarchical":[51],"Emotion-Guided":[52],"Masked":[53],"Transformer":[54],"tackles":[56],"these":[57],"limitations.":[58],"We":[59],"introduce":[60],"Mask-Based":[62],"Motion":[63],"Modeling":[64],"Strategy":[65],"in":[66,162],"discrete":[68],"latent":[69],"space,":[70],"enabling":[71],"learning":[72,124],"from":[73,118],"partially":[74,149],"annotated":[75,150],"ensuring":[78],"physically":[79],"plausible":[80],"motions":[81],"under":[82],"incomplete":[83],"supervision,":[84],"alongside":[85],"hierarchical":[87],"Emotion":[88],"Guidance":[89],"Adaptor":[90],"injects":[92],"time-varying":[93],"cues":[95],"at":[96],"multiple":[97],"transformer":[98],"levels,":[99],"capturing":[100],"both":[101],"global":[102],"subtle":[105],"local":[106],"nuances.":[107],"An":[108],"Alternating":[109],"Optimization":[110],"Mechanism":[111],"is":[112],"employed":[113],"decouple":[115],"semantic":[116],"alignment":[117],"modulation":[120],"during":[121],"training,":[122],"stabilizing":[123],"improving":[126],"expression":[127],"fidelity.":[128],"At":[129],"inference,":[130],"Mask-Guided":[132],"Inference":[133],"strategy":[134],"seamlessly":[135],"extends":[136],"gestures":[137],"over":[138],"long":[139],"sequences,":[140],"mitigating":[141],"boundary":[142],"discontinuities":[143],"drift.":[145],"Evaluations":[146],"on":[147],"dataset":[151],"featuring":[152],"natural":[153],"transitions":[155],"show":[156],"our":[157],"surpasses":[159],"existing":[160],"approaches":[161],"generation,":[166],"yielding":[167],"improved":[168],"gestures-peech":[169],"synchrony,":[170],"enhanced":[171],"diversity,":[173],"more":[175],"faithful":[176],"emotion-conveying":[177],"ability.":[178]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}