{"id":"https://openalex.org/W7137886631","doi":"https://doi.org/10.1609/aaai.v40i16.38327","title":"DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model","display_name":"DialoGen: Towards Dialog Gesture Generation via Identity-Decoupled Style Guidance in Interactive Diffusion Model","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137886631","doi":"https://doi.org/10.1609/aaai.v40i16.38327"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38327","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38327","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i16.38327","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002473193","display_name":"Weiyu Zhao","orcid":"https://orcid.org/0009-0002-2661-3692"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiyu Zhao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739435","display_name":"Chenyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084899380","display_name":"Liangxiao Hu","orcid":"https://orcid.org/0000-0001-5233-473X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangxiao Hu","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730043","display_name":"Zonglin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonglin Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659355","display_name":"Wei Yu","orcid":null},"institutions":[{"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":"Wei Yu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084025984","display_name":"Shengping Zhang","orcid":"https://orcid.org/0000-0001-5200-3420"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengping Zhang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002473193"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10516252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13253","last_page":"13261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.23119999468326569,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.23119999468326569,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.14499999582767487,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11789999902248383,"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":0.8906999826431274},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8511999845504761},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6669999957084656},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46619999408721924}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8906999826431274},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8511999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6669999957084656},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5073000192642212},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4521999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.444599986076355},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4293999969959259},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C106624574","wikidata":"https://www.wikidata.org/wiki/Q5270387","display_name":"Diagrammatic reasoning","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38327","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38327","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38327","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38327","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"DialoGen,":[2],"a":[3,28,123],"novel":[4],"framework":[5],"for":[6,10,36,126],"generating":[7,117],"realistic":[8],"gestures":[9,35,46],"both":[11,37],"interlocutors":[12,96],"in":[13,116],"dialog":[14,102,128],"scenarios,":[15],"conditioned":[16],"on":[17,27],"conversational":[18],"audios.":[19],"Unlike":[20],"most":[21],"existing":[22,114],"methods":[23,115],"that":[24,47,109],"focus":[25],"solely":[26],"single":[29],"speaker,":[30],"DialoGen":[31,58],"simultaneously":[32],"generates":[33],"synchronized":[34],"participants":[38],"while":[39],"also":[40],"embedding":[41],"identity-decoupled":[42,86],"style":[43,87,94],"into":[44,72,97],"generated":[45],"enhance":[48],"realism":[49],"and":[50],"expressiveness.":[51],"To":[52],"ensure":[53],"precise":[54],"synchronization":[55],"between":[56],"interlocutors,":[57],"adopts":[59],"an":[60],"interactive":[61],"dual-diffusion":[62],"model":[63,111],"with":[64],"mutual":[65],"interaction":[66,70],"estimation,":[67],"which":[68],"integrates":[69],"correlation":[71],"the":[73,85,92],"diffusion":[74],"process.":[75],"More":[76],"importantly,":[77],"by":[78],"leveraging":[79],"supervised":[80],"contrastive":[81],"learning,":[82],"we":[83],"develop":[84],"guidance":[88],"to":[89],"adaptively":[90],"decompose":[91],"identity-specific":[93,120],"of":[95],"latent":[98],"space,":[99],"enabling":[100],"multi-style":[101],"gesture":[103],"generation.":[104],"Extensive":[105],"experimental":[106],"results":[107],"demonstrate":[108],"our":[110],"significantly":[112],"outperforms":[113],"realistic,":[118],"speech-aligned,":[119],"gestures,":[121],"offering":[122],"high-quality":[124],"solution":[125],"various":[127],"scenarios.":[129]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}
