{"id":"https://openalex.org/W7125930751","doi":"https://doi.org/10.1109/smc58881.2025.11343724","title":"Fine-Grained Action Recognition Using Cross-Modal Attention Network for Human-Robot Sign Language Interaction","display_name":"Fine-Grained Action Recognition Using Cross-Modal Attention Network for Human-Robot Sign Language Interaction","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125930751","doi":"https://doi.org/10.1109/smc58881.2025.11343724"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124134132","display_name":"Jing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Hu","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124075027","display_name":"Qing Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Gao","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070050027","display_name":"Xi Cheng","orcid":"https://orcid.org/0000-0003-3081-3750"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianfeng Cheng","raw_affiliation_strings":["Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108255872","display_name":"Xuerui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuerui Li","raw_affiliation_strings":["University at Buffalo,Department of Computer Science and Engineering,Buffalo,NY,United States,14221"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo,Department of Computer Science and Engineering,Buffalo,NY,United States,14221","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056287221","display_name":"Zhaojie Ju","orcid":"https://orcid.org/0000-0002-9524-7609"},"institutions":[{"id":"https://openalex.org/I63072094","display_name":"University of Portsmouth","ror":"https://ror.org/03ykbk197","country_code":"GB","type":"education","lineage":["https://openalex.org/I63072094"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhaojie Ju","raw_affiliation_strings":["University of Portsmouth,School of Computing,Portsmouth,UK,PO13HE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Portsmouth,School of Computing,Portsmouth,UK,PO13HE","institution_ids":["https://openalex.org/I63072094"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"7447","last_page":"7453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.8313000202178955,"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":0.8313000202178955,"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":0.10790000110864639,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.015599999576807022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.6236000061035156},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5627999901771545},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5616000294685364},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5228000283241272},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5012999773025513},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723800003528595},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5616000294685364},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5221999883651733},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4697999954223633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6154322624206543}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1871419576","https://openalex.org/W2012557818","https://openalex.org/W2013637713","https://openalex.org/W2024566152","https://openalex.org/W2293474797","https://openalex.org/W2309561466","https://openalex.org/W2520114359","https://openalex.org/W2528925775","https://openalex.org/W2751841288","https://openalex.org/W2776217220","https://openalex.org/W2810685774","https://openalex.org/W2921102529","https://openalex.org/W2921151905","https://openalex.org/W2928645920","https://openalex.org/W2953787907","https://openalex.org/W2963076818","https://openalex.org/W2990654629","https://openalex.org/W2993585638","https://openalex.org/W2999443412","https://openalex.org/W3003646123","https://openalex.org/W3009828227","https://openalex.org/W3014641072","https://openalex.org/W3016234935","https://openalex.org/W3097430769","https://openalex.org/W3130218528","https://openalex.org/W3195949276","https://openalex.org/W4282981352","https://openalex.org/W4297094621","https://openalex.org/W4312245820","https://openalex.org/W4378746725","https://openalex.org/W4385245566","https://openalex.org/W4391307620","https://openalex.org/W4391324012","https://openalex.org/W4406611397","https://openalex.org/W4406612712","https://openalex.org/W4406613993"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,8,95,103,165,185,201,217,227,237,244],"growing":[2],"demand":[3],"for":[4,32,117],"barrier-free":[5],"communication":[6],"among":[7],"deaf":[9,48],"and":[10,43,71,140,148,190,246],"mute,":[11],"human-robot":[12],"sign":[13,233],"language":[14,234],"interaction":[15,46],"has":[16],"gradually":[17],"gained":[18],"attention":[19],"as":[20,27,172],"an":[21],"auxiliary":[22],"tool.":[23],"Action":[24],"recognition":[25,61,82,130],"serves":[26],"a":[28,118,127,153,176],"crucial":[29],"information":[30,209],"source":[31],"robots":[33,39,111],"to":[34,40,69,73,90,112,114,162,183],"understand":[35],"human":[36,66,123,159,238],"behavior,":[37],"enabling":[38],"recognize":[41],"signs":[42],"achieve":[44],"natural":[45],"with":[47,236],"people":[49],"through":[50],"it.":[51],"However,":[52],"existing":[53],"Human-Robot":[54],"Interaction":[55,178],"(HRI)":[56],"technologies":[57],"based":[58,137],"on":[59,64,138,216],"action":[60,81,129,220],"mainly":[62],"focus":[63],"coarse-grained":[65],"movements,":[67],"failing":[68],"capture":[70],"respond":[72],"nuanced":[74,120],"actions":[75,239],"in":[76,102,200,252],"real-world":[77,253],"scenarios.":[78,254],"Additionally,":[79],"multi-modal":[80],"often":[83],"employs":[84],"early":[85],"or":[86],"late":[87],"fusion":[88],"methods":[89],"integrate":[91],"various":[92],"modalities,":[93,100],"lacking":[94],"exploration":[96],"of":[97,105,122,195,204,248],"relationships":[98],"between":[99,188],"resulting":[101],"loss":[104],"some":[106],"correlated":[107],"information.":[108],"To":[109],"enable":[110],"adapt":[113],"diverse":[115],"scenarios":[116],"more":[119],"understanding":[121],"behaviors,":[124],"we":[125],"propose":[126],"fine-grained":[128,167,219],"framework":[131],"using":[132],"Cross-Modal":[133],"Attention":[134],"network":[135],"(CMA)":[136],"RGB":[139,189],"skeleton.":[141],"Firstly,":[142],"holistic":[143],"features":[144,199],"including":[145],"face,":[146],"hand,":[147],"body":[149],"are":[150,214],"extracted":[151,166],"by":[152,231,241],"pose":[154],"estimator,":[155],"effectively":[156],"representing":[157],"intricate":[158],"actions.":[160],"Subsequently,":[161],"fully":[163],"leverage":[164],"features,":[168],"skeleton":[169],"is":[170,181],"represented":[171],"heatmap":[173],"volumes.":[174],"Finally,":[175],"Cross-Attention":[177],"(CAI)":[179],"module":[180],"designed":[182],"explore":[184],"intrinsic":[186],"connections":[187],"skeleton,":[191],"facilitating":[192],"mutual":[193],"learning":[194],"their":[196],"respective":[197],"advantageous":[198],"deep":[202],"layers":[203],"feature":[205],"extraction,":[206],"thereby":[207],"achieving":[208],"interaction.":[210],"Simultaneously,":[211],"HRI":[212,225],"experiments":[213],"conducted":[215],"large-scale":[218],"dataset,":[221],"WLASL2000.":[222],"In":[223],"this":[224],"system,":[226],"robotic":[228],"arm":[229],"responds":[230],"performing":[232],"aligned":[235],"identified":[240],"CMA,":[242],"showcasing":[243],"practicality":[245],"effectiveness":[247],"our":[249],"proposed":[250],"model":[251]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}