{"id":"https://openalex.org/W4415708026","doi":"https://doi.org/10.1109/icme59968.2025.11209046","title":"Hierarchical Sub-action Tree for Continuous Sign Language Recognition","display_name":"Hierarchical Sub-action Tree for Continuous Sign Language Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708026","doi":"https://doi.org/10.1109/icme59968.2025.11209046"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209046","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5012758803","display_name":"Dejie Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dejie Yang","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109104700","display_name":"Xu Zhu","orcid":"https://orcid.org/0009-0003-4546-4810"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Xu","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113213656","display_name":"Xinjie Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinjie Gao","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-4242-4840"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Peking University,Wangxuan Institute of Computer Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012758803"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30936831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9948999881744385,"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":0.9948999881744385,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T10789","display_name":"Interactive and Immersive Displays","score":0.000699999975040555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.6396999955177307},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.527899980545044},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5097000002861023},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4837000072002411},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.39800000190734863},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.39100000262260437},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.37139999866485596},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593999862670898},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6129000186920166},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5097000002861023},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.39800000190734863},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209046","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2188882108","https://openalex.org/W2746301562","https://openalex.org/W2759302818","https://openalex.org/W2799020610","https://openalex.org/W2948139159","https://openalex.org/W2997931247","https://openalex.org/W3092363664","https://openalex.org/W3147467731","https://openalex.org/W3173290664","https://openalex.org/W3203359574","https://openalex.org/W4312910375","https://openalex.org/W4382240684","https://openalex.org/W4386065518","https://openalex.org/W4386071548","https://openalex.org/W4390873469","https://openalex.org/W4390873551","https://openalex.org/W4393154516","https://openalex.org/W4393156256","https://openalex.org/W4394711874"],"related_works":[],"abstract_inverted_index":{"Continuous":[0],"sign":[1],"language":[2,95],"recognition":[3],"(CSLR)":[4],"aims":[5],"to":[6,36,49,80,125,136],"transcribe":[7],"untrimmed":[8],"videos":[9],"into":[10],"glosses,":[11],"which":[12],"are":[13,164],"typically":[14,57],"textual":[15,53,59,100,110,116],"words.":[16],"Recent":[17],"studies":[18],"indicate":[19],"that":[20],"the":[21,73,122,138,141,156],"lack":[22],"of":[23,158],"large":[24,94],"datasets":[25,147],"and":[26,52,115,119,151,162],"precise":[27],"annotations":[28],"has":[29],"become":[30],"a":[31,132],"bottleneck":[32],"for":[33,109],"CSLR":[34],"due":[35],"insufficient":[37],"training":[38],"data.":[39],"To":[40],"address":[41],"this,":[42],"some":[43],"works":[44],"have":[45],"developed":[46],"cross-modal":[47],"solutions":[48],"align":[50],"visual":[51,86,114],"modalities.":[54,143],"However,":[55],"they":[56],"extract":[58],"features":[60],"from":[61,93,121],"glosses":[62],"without":[63],"fully":[64],"utilizing":[65],"their":[66],"knowledge.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,105,130],"propose":[72],"Hierarchical":[74],"Sub-action":[75],"Tree":[76],"(HST),":[77],"termed":[78],"HST-CSLR,":[79],"efficiently":[81],"combine":[82],"gloss":[83],"knowledge":[84,92],"with":[85],"representation":[87],"learning.":[88],"By":[89],"incorporating":[90],"gloss-specific":[91],"models,":[96],"our":[97,159],"approach":[98],"leverages":[99],"information":[101,111],"more":[102],"effectively.":[103],"Specifically,":[104],"construct":[106],"an":[107],"HST":[108],"representation,":[112],"aligning":[113],"modalities":[117],"step-by-step":[118],"benefiting":[120],"tree":[123],"structure":[124],"reduce":[126],"computational":[127],"complexity.":[128],"Additionally,":[129],"impose":[131],"contrastive":[133],"alignment":[134],"enhancement":[135],"bridge":[137],"gap":[139],"between":[140],"two":[142],"Experiments":[144],"on":[145],"four":[146],"(PHOENIX-2014,":[148],"PHOENIX-2014T,":[149],"CSL-Daily,":[150],"Sign":[152],"Language":[153],"Gesture)":[154],"demonstrate":[155],"effectiveness":[157],"HST-CSLR.":[160],"Code":[161],"model":[163],"available":[165],"at:":[166],"https://github.com/Federfallt/HST-CSLR.git.":[167]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}