{"id":"https://openalex.org/W4414360562","doi":"https://doi.org/10.24963/ijcai.2025/276","title":"Open-Vocabulary Fine-Grained Hand Action Detection","display_name":"Open-Vocabulary Fine-Grained Hand Action Detection","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360562","doi":"https://doi.org/10.24963/ijcai.2025/276"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/276","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076042294","display_name":"Ting Zhe","orcid":"https://orcid.org/0000-0002-3478-5921"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ting Zhe","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065577924","display_name":"Mengya Han","orcid":"https://orcid.org/0000-0003-3499-3832"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mengya Han","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037323143","display_name":"Xiaoshuai Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Hao","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039158745","display_name":"Yong Luo","orcid":"https://orcid.org/0000-0002-2296-6370"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yong Luo","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103675907","display_name":"Zheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Zheng He","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003753939","display_name":"Xiantao Cai","orcid":"https://orcid.org/0000-0002-0764-5085"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Xiantao Cai","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2476","last_page":"2484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9934999942779541,"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":0.9934999942779541,"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":0.9919000267982483,"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/action","display_name":"Action (physics)","score":0.6703000068664551},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5662999749183655},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5356000065803528},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5277000069618225},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.451200008392334},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/unison","display_name":"Unison","score":0.4311000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932999730110168},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6703000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.614300012588501},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4332999885082245},{"id":"https://openalex.org/C2780304638","wikidata":"https://www.wikidata.org/wiki/Q176224","display_name":"Unison","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.36899998784065247},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/276","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"In":[0],"this":[1],"work,":[2],"we":[3,96,136],"address":[4,93],"the":[5,161],"new":[6],"challenge":[7],"of":[8,165],"open-vocabulary":[9,54,130,183],"fine-grained":[10,68,110,131,167],"hand":[11,18,30,49,132,184],"action":[12,31,50,69,133,185],"detection,":[13,38],"which":[14,106],"aims":[15],"to":[16,36,44,46,81,108,159],"recognize":[17],"actions":[19],"from":[20,115],"both":[21],"known":[22],"and":[23,76,84,89,147,150,163],"novel":[24,62,90,99],"categories":[25],"using":[26],"textual":[27],"descriptions.":[28],"Traditional":[29],"detection":[32,55],"methods":[33,57],"are":[34,58],"limited":[35,75,116],"closed-set":[37],"making":[39],"it":[40],"difficult":[41],"for":[42,182],"them":[43],"generalize":[45],"new,":[47],"unseen":[48],"categories.":[51,91],"While":[52],"current":[53],"(OVD)":[56],"effective":[59],"at":[60,192],"detecting":[61],"objects,":[63],"they":[64],"face":[65],"challenges":[66],"with":[67],"recognition,":[70],"particularly":[71],"when":[72],"data":[73],"is":[74,190],"heterogeneous.":[77],"This":[78],"often":[79],"leads":[80],"poor":[82],"generalization":[83],"performance":[85],"bias":[86],"between":[87],"base":[88],"To":[92],"these":[94,126],"issues,":[95],"propose":[97],"a":[98],"approach,":[100],"Open-FGHA":[101,173],"(Open-vocabulary":[102],"Fine-Grained":[103],"Hand":[104],"Action),":[105],"learns":[107],"distinguish":[109],"features":[111],"across":[112],"multiple":[113],"modalities":[114],"heterogeneous":[117],"data.":[118],"It":[119],"then":[120],"identifies":[121],"optimal":[122],"matching":[123],"relationships":[124],"among":[125],"features,":[127],"enabling":[128],"accurate":[129],"detection.":[134,186],"Specifically,":[135],"introduce":[137],"three":[138],"key":[139],"components:":[140],"Hierarchical":[141],"Heterogeneous":[142],"Low-Rank":[143],"Adaptation,":[144],"Bidirectional":[145],"Selection":[146],"Fusion":[148],"Mechanism,":[149],"Cross-Modality":[151],"Query":[152],"Generator.":[153],"These":[154],"components":[155],"work":[156],"in":[157],"unison":[158],"enhance":[160],"alignment":[162],"fusion":[164],"multimodal":[166],"features.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"that":[172],"outperforms":[174],"existing":[175],"OVD":[176],"methods,":[177],"showing":[178],"its":[179],"strong":[180],"potential":[181],"The":[187],"source":[188],"code":[189],"available":[191],"OV-FGHAD.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}