{"id":"https://openalex.org/W4304091498","doi":"https://doi.org/10.1145/3503161.3548213","title":"Weakly-supervised Disentanglement Network for Video Fingerspelling Detection","display_name":"Weakly-supervised Disentanglement Network for Video Fingerspelling Detection","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091498","doi":"https://doi.org/10.1145/3503161.3548213"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548213","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5107809094","display_name":"Ziqi Jiang","orcid":"https://orcid.org/0000-0001-7041-627X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqi Jiang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757086","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0001-7480-398X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936507","display_name":"Siyuan Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Yao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082131901","display_name":"Wenqiao Zhang","orcid":"https://orcid.org/0000-0002-5988-7609"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenqiao Zhang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621218","display_name":"Sihan Zhang","orcid":"https://orcid.org/0000-0002-1561-6241"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihan Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Shanghai Institute for Advanced Study of Zhejiang University & Shanghai AI Laboratory, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute for Advanced Study of Zhejiang University & Shanghai AI Laboratory, Hangzhou, China","institution_ids":["https://openalex.org/I4210111959","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5107809094"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.5304,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.56758338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5446","last_page":"5455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":1.0,"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":1.0,"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":0.9936000108718872,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.8696205615997314},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6727414131164551},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.6374835968017578},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5929407477378845},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5517145395278931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5287415981292725},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49735143780708313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4691174328327179},{"id":"https://openalex.org/keywords/american-sign-language","display_name":"American Sign Language","score":0.455809086561203},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.45328289270401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38999316096305847},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2334422767162323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696205615997314},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6727414131164551},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.6374835968017578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5929407477378845},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5517145395278931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5287415981292725},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49735143780708313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4691174328327179},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.455809086561203},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.45328289270401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38999316096305847},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2334422767162323},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548213","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1580385328","https://openalex.org/W1979437380","https://openalex.org/W1985408783","https://openalex.org/W1993928670","https://openalex.org/W2108598243","https://openalex.org/W2127141656","https://openalex.org/W2151103935","https://openalex.org/W2188882108","https://openalex.org/W2342890612","https://openalex.org/W2463640844","https://openalex.org/W2524643686","https://openalex.org/W2531638282","https://openalex.org/W2607059968","https://openalex.org/W2755802490","https://openalex.org/W2771976988","https://openalex.org/W2895638065","https://openalex.org/W2963163009","https://openalex.org/W2963169737","https://openalex.org/W2963247196","https://openalex.org/W2963408148","https://openalex.org/W2964162626","https://openalex.org/W2991087169","https://openalex.org/W3009828227","https://openalex.org/W3027790991","https://openalex.org/W3034549794","https://openalex.org/W3035101153","https://openalex.org/W3048921104","https://openalex.org/W3092659741","https://openalex.org/W3106477714","https://openalex.org/W3108425892","https://openalex.org/W3126423526","https://openalex.org/W3152500092","https://openalex.org/W3154508774","https://openalex.org/W3173204563","https://openalex.org/W3176441955","https://openalex.org/W4214951593","https://openalex.org/W4285345683","https://openalex.org/W4304084069","https://openalex.org/W4312245888"],"related_works":["https://openalex.org/W4308478915","https://openalex.org/W4389049376","https://openalex.org/W1986488374","https://openalex.org/W2064351213","https://openalex.org/W2089405242","https://openalex.org/W2004685257","https://openalex.org/W2954293526","https://openalex.org/W1977288663","https://openalex.org/W2115068291","https://openalex.org/W3010360921"],"abstract_inverted_index":{"Fingerspelling":[0],"detection,":[1],"which":[2,102,168],"aims":[3],"to":[4,37,118,129,141,154,217],"localize":[5],"and":[6,31,45,58,85,123,161,177,183,201,224],"recognize":[7],"fingerspelling":[8,222],"gestures":[9],"in":[10,52,114,135],"raw,":[11],"untrimmed":[12],"videos,":[13],"is":[14],"a":[15,104,119,155,187],"nascent":[16],"but":[17],"important":[18],"research":[19],"area":[20],"that":[21,64,80,131,207],"could":[22],"help":[23],"bridge":[24],"the":[25,74,88,115,136,142,145,149,163,170,198,208,218],"communication":[26],"gap":[27],"between":[28],"deaf":[29],"people":[30],"others.":[32],"Many":[33],"existing":[34],"works":[35],"tend":[36],"exploit":[38],"additional":[39,55,83],"knowledge,":[40,84],"such":[41],"as":[42,174],"pose":[43],"annotations,":[44],"newly":[46],"datasets":[47],"for":[48,107,179,221],"performance":[49,220],"improvement.":[50],"However,":[51],"real-world":[53],"applications,":[54],"data":[56],"collection":[57],"annotation":[59],"require":[60],"tremendous":[61],"human":[62],"efforts":[63],"are":[65],"not":[66,133],"always":[67],"affordable.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,124],"propose":[73],"Weakly-supervised":[75],"Disentanglement":[76,100],"Network,":[77],"namely":[78],"WED,":[79],"requires":[81],"no":[82],"better":[86,156],"exploits":[87],"video-sentence":[89,150],"weak":[90,151],"supervisions.":[91],"Specifically,":[92],"WED":[93,209],"incorporates":[94],"two":[95],"critical":[96],"components:":[97],"1)":[98],"Masked":[99],"Module,":[101],"employs":[103],"Variational":[105],"Autoencoder":[106],"signed":[108,121],"letters":[109,130],"disentanglement.":[110],"Each":[111],"latent":[112,126],"factor":[113],"VAE":[116],"corresponds":[117],"particular":[120],"letter,":[122],"mask":[125],"factors":[127],"corresponding":[128],"do":[132],"appear":[134],"video":[137],"during":[138],"decoding.":[139],"Compared":[140],"vanilla":[143],"VAE,":[144],"masked":[146],"reconstruction":[147],"leverages":[148,169],"supervision,":[152],"leading":[153],"sign":[157,172,213],"language":[158],"oriented":[159],"disentanglement;":[160],"2)":[162],"Dynamic":[164],"Memory":[165],"Network":[166],"module,":[167],"disentangled":[171],"knowledge":[173,176],"prior":[175],"reference":[178],"sign-related":[180],"frame":[181],"identification":[182],"gesture":[184,214],"recognition":[185],"through":[186],"carefully":[188],"designed":[189],"memory":[190],"reading":[191],"component.":[192],"We":[193],"conduct":[194],"extensive":[195],"experiments":[196],"on":[197],"benchmark":[199],"ChicagoFSWild":[200],"ChicagoFSWild+":[202],"datasets.":[203],"Empirical":[204],"studies":[205],"validate":[206],"network":[210],"achieves":[211],"effective":[212],"disentanglement,":[215],"contributing":[216],"state-of-the-art":[219],"detection":[223],"recognition.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}