{"id":"https://openalex.org/W4405766234","doi":"https://doi.org/10.1109/iccv51701.2025.01277","title":"SemTalk: Holistic Co-Speech Motion Generation with Frame-Level Semantic Emphasis","display_name":"SemTalk: Holistic Co-Speech Motion Generation with Frame-Level Semantic Emphasis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405766234","doi":"https://doi.org/10.1109/iccv51701.2025.01277"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.16563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009013564","display_name":"Xiangyue Zhang","orcid":"https://orcid.org/0000-0002-4517-6777"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangyue Zhang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023574396","display_name":"Jiangfang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfang Li","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777142","display_name":"Jiaxu Zhang","orcid":"https://orcid.org/0000-0002-4732-2168"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Zhang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436855","display_name":"Zheng Dang","orcid":"https://orcid.org/0000-0003-3841-7912"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqiang Dang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112108215","display_name":"Jianqiang Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianqiang Ren","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085032007","display_name":"Liefeng Bo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liefeng Bo","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074405661","display_name":"Zhigang Tu","orcid":"https://orcid.org/0000-0001-5003-2260"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Tu","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5009013564"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":1.0652,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73250611,"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":"13761","last_page":"13771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.989799976348877,"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":0.989799976348877,"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":0.9861999750137329,"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/T12031","display_name":"Speech and dialogue systems","score":0.9656999707221985,"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/emphasis","display_name":"Emphasis (telecommunications)","score":0.8431123495101929},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5899865031242371},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.544712483882904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5131931900978088},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3487268090248108},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34579336643218994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28782492876052856},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1170985996723175},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09234514832496643}],"concepts":[{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.8431123495101929},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5899865031242371},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.544712483882904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5131931900978088},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3487268090248108},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34579336643218994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28782492876052856},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1170985996723175},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09234514832496643}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.16563","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.16563","pdf_url":"https://arxiv.org/pdf/2412.16563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"doi:10.48550/arxiv.2412.16563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.16563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.16563","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.16563","pdf_url":"https://arxiv.org/pdf/2412.16563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4423990031","display_name":null,"funder_award_id":"624B2110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6891033150","display_name":null,"funder_award_id":"2024YFC3015600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335581","display_name":"Young Scientists Fund","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2055105357","https://openalex.org/W2153819599","https://openalex.org/W2255426644","https://openalex.org/W4390911758","https://openalex.org/W2072124641","https://openalex.org/W2167093538","https://openalex.org/W2018956713","https://openalex.org/W2081479354","https://openalex.org/W2113107605","https://openalex.org/W3204693335"],"abstract_inverted_index":{"A":[0],"good":[1],"co-speech":[2,30,109,138],"motion":[3,15,31,101,105,139],"generation":[4,32],"cannot":[5],"be":[6],"achieved":[7],"without":[8],"a":[9,71,114,145],"careful":[10],"integration":[11],"of":[12],"common":[13],"rhythmic":[14,60],"and":[16,46,49,59,106,122],"rare":[17],"yet":[18],"essential":[19],"semantic":[20,35,82,95,116,142],"motion.":[21,148],"In":[22,54],"this":[23],"work,":[24],"we":[25,111],"propose":[26],"SemTalk":[27],"for":[28,118],"holistic":[29],"with":[33,77,140],"frame-level":[34,94],"emphasis.":[36],"Our":[37],"key":[38],"insight":[39],"is":[40,85],"to":[41,65,87,98],"separately":[42],"learn":[43],"base":[44,68,104,147],"motions":[45],"sparse":[47,90,100],"motions,":[48],"then":[50],"adaptively":[51],"fuse":[52],"them.":[53],"particular,":[55],"coarse2fine":[56],"cross-attention":[57],"module":[58],"consistency":[61],"learning":[62,84],"are":[63],"explored":[64],"establish":[66],"rhythm-related":[67],"motion,":[69,91],"ensuring":[70],"coherent":[72],"foundation":[73],"that":[74,130],"synchronizes":[75],"gestures":[76],"the":[78,103,134],"speech":[79],"rhythm.":[80],"Subsequently,":[81],"emphasis":[83],"designed":[86],"generate":[88,107],"semantic-aware":[89],"focusing":[92],"on":[93,125],"cues.":[96],"Finally,":[97],"integrate":[99],"into":[102],"semantic-emphasized":[108],"gestures,":[110],"further":[112],"leverage":[113],"learned":[115],"score":[117],"adaptive":[119],"synthesis.":[120],"Qualitative":[121],"quantitative":[123],"comparisons":[124],"two":[126],"public":[127],"datasets":[128],"demonstrate":[129],"our":[131],"method":[132],"outperforms":[133],"state-of-the-art,":[135],"delivering":[136],"high-quality":[137],"enhanced":[141],"richness":[143],"over":[144],"stable":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
