{"id":"https://openalex.org/W4415518749","doi":"https://doi.org/10.1145/3746268.3759436","title":"SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain","display_name":"SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain","publication_year":2025,"publication_date":"2025-10-24","ids":{"openalex":"https://openalex.org/W4415518749","doi":"https://doi.org/10.1145/3746268.3759436"},"language":null,"primary_location":{"id":"doi:10.1145/3746268.3759436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746268.3759436","pdf_url":null,"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 International Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746268.3759436","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103218361","display_name":"Nan Gao","orcid":"https://orcid.org/0000-0002-8277-4100"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nan Gao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024817565","display_name":"Yihua Bao","orcid":"https://orcid.org/0000-0002-4250-2258"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Bao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080838784","display_name":"Dongdong Weng","orcid":"https://orcid.org/0000-0003-2352-0896"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Weng","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102608993","display_name":"Jiayi Zhao","orcid":"https://orcid.org/0009-0007-3789-000X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Zhao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054585200","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-6077-7896"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Lenovo, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Lenovo, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103282189","display_name":"Yan Zhou","orcid":"https://orcid.org/0009-0002-0564-0915"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhou","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928510","display_name":"Pengfei Wan","orcid":"https://orcid.org/0000-0001-7225-565X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wan","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103218361"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30720294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.933899998664856},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6618000268936157},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5871000289916992},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.550000011920929},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4138000011444092},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.39750000834465027}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.933899998664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800000011920929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6955999732017517},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6618000268936157},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738999843597412},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746268.3759436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746268.3759436","pdf_url":null,"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 International Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746268.3759436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746268.3759436","pdf_url":null,"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 International Workshop on Generation and Evaluation of Non-verbal Behaviour for Embodied Agents","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W14706657","https://openalex.org/W1969681536","https://openalex.org/W2054255259","https://openalex.org/W3083173864","https://openalex.org/W3124346429","https://openalex.org/W3194357576","https://openalex.org/W4312584365","https://openalex.org/W4377010269","https://openalex.org/W4385284180","https://openalex.org/W4400822426"],"related_works":[],"abstract_inverted_index":{"Co-speech":[0],"gesture":[1,9,45,62,77,92,105,127,149],"generation":[2,107,113],"enhances":[3],"human-computer":[4],"interaction":[5],"realism":[6],"through":[7],"speech-synchronized":[8],"synthesis.":[10],"However,":[11],"generating":[12,42],"semantically":[13,117],"meaningful":[14,53],"gestures":[15],"remains":[16],"a":[17,23,59,97,103],"challenging":[18],"problem.":[19],"We":[20],"propose":[21],"SARGes,":[22],"novel":[24],"framework":[25],"that":[26,72,124],"leverages":[27],"large":[28],"language":[29],"models":[30],"(LLMs)":[31],"to":[32,89,131],"construct":[33],"an":[34,66],"intent":[35,68,134],"chain":[36,69],"for":[37],"parsing":[38],"speech":[39],"content":[40],"and":[41,64,75,101,116,142],"reliable":[43],"semantic":[44,146],"labels,":[46],"which":[47,109],"subsequently":[48],"guide":[49],"the":[50,112,145],"synthesis":[51],"of":[52,114,148],"co-speech":[54,61,119],"gestures.":[55,120],"First,":[56],"we":[57,95],"constructed":[58,96],"comprehensive":[60],"ethogram":[63,84],"developed":[65],"LLM-based":[67],"reasoning":[70],"mechanism":[71],"systematically":[73],"parses":[74],"decomposes":[76],"semantics":[78],"into":[79],"structured":[80],"inference":[81,139],"steps":[82],"following":[83],"criteria,":[85],"effectively":[86],"guiding":[87],"LLMs":[88],"parse":[90],"context-aware":[91],"labels.":[93],"Subsequently,":[94],"text-to-gesture":[98],"label":[99,106],"dataset":[100],"trained":[102],"lightweight":[104],"model,":[108],"then":[110],"guides":[111],"credible":[115],"coherent":[118],"Experimental":[121],"results":[122],"show":[123],"SARGes":[125],"achieves":[126],"labeling":[128],"performance":[129],"comparable":[130],"GPT-4":[132],"in":[133],"interpretation,":[135],"with":[136],"efficient":[137],"single-pass":[138],"(0.4":[140],"seconds),":[141],"significantly":[143],"improves":[144],"expressiveness":[147],"generation.":[150]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-24T00:00:00"}