{"id":"https://openalex.org/W4399167881","doi":"https://doi.org/10.1109/tip.2024.3404869","title":"Gloss Prior Guided Visual Feature Learning for Continuous Sign Language Recognition","display_name":"Gloss Prior Guided Visual Feature Learning for Continuous Sign Language Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399167881","doi":"https://doi.org/10.1109/tip.2024.3404869","pmid":"https://pubmed.ncbi.nlm.nih.gov/38814773"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3404869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3404869","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5075792265","display_name":"Leming Guo","orcid":"https://orcid.org/0000-0001-7569-6928"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leming Guo","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7569-6928","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027220635","display_name":"Wanli Xue","orcid":"https://orcid.org/0000-0002-6031-9334"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanli Xue","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-6031-9334","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115587783","display_name":"\u0411\u043e \u041b\u044e","orcid":"https://orcid.org/0000-0003-3045-628X"},"institutions":[{"id":"https://openalex.org/I1330693074","display_name":"Walmart (United States)","ror":"https://ror.org/04j0gge90","country_code":"US","type":"company","lineage":["https://openalex.org/I1330693074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Walmart Global Tech, Sunnyvale, CA, USA","JD Finance America Corporation, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Walmart Global Tech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1330693074"]},{"raw_affiliation_string":"JD Finance America Corporation, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075412755","display_name":"Kaihua Zhang","orcid":"https://orcid.org/0000-0002-1613-3401"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaihua Zhang","raw_affiliation_strings":["School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1613-3401","affiliations":[{"raw_affiliation_string":"School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715982","display_name":"Tiantian Yuan","orcid":"https://orcid.org/0000-0002-2532-3514"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Yuan","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-2532-3514","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109600054","display_name":"Dimitris Metaxas","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitris Metaxas","raw_affiliation_strings":["Department of Computer Science, Rutgers University, Piscataway, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3201,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91626376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"3486","last_page":"3495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"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":0.9998999834060669,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9764000177383423,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gloss","display_name":"Gloss (optics)","score":0.7675591707229614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.720668613910675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.670876145362854},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5922479629516602},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5282227993011475},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.5140929818153381},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44919678568840027},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3630920648574829}],"concepts":[{"id":"https://openalex.org/C143025027","wikidata":"https://www.wikidata.org/wiki/Q900581","display_name":"Gloss (optics)","level":3,"score":0.7675591707229614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720668613910675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.670876145362854},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5922479629516602},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5282227993011475},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5140929818153381},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44919678568840027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3630920648574829},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2781448156","wikidata":"https://www.wikidata.org/wiki/Q1570182","display_name":"Coating","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3404869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3404869","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:38814773","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38814773","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1592249304","display_name":null,"funder_award_id":"62020106004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2840396449","display_name":null,"funder_award_id":"62276141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5370040448","display_name":null,"funder_award_id":"92048301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G586450310","display_name":null,"funder_award_id":"23JCYBJC00360","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"},{"id":"https://openalex.org/G7718971067","display_name":null,"funder_award_id":"2021YJSB244","funder_id":"https://openalex.org/F4320336754","funder_display_name":"Tianjin Research Innovation Project for Postgraduate Students"},{"id":"https://openalex.org/G8062198870","display_name":null,"funder_award_id":"62376197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336754","display_name":"Tianjin Research Innovation Project for Postgraduate Students","ror":null},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2139501017","https://openalex.org/W2188882108","https://openalex.org/W2788334925","https://openalex.org/W2799020610","https://openalex.org/W2807840688","https://openalex.org/W2890208366","https://openalex.org/W2896457183","https://openalex.org/W2908497602","https://openalex.org/W2941870244","https://openalex.org/W2948139159","https://openalex.org/W2963446712","https://openalex.org/W2963853051","https://openalex.org/W2964253156","https://openalex.org/W2964452558","https://openalex.org/W2965778995","https://openalex.org/W2997136715","https://openalex.org/W2997931247","https://openalex.org/W3021636956","https://openalex.org/W3033228789","https://openalex.org/W3034765865","https://openalex.org/W3034772468","https://openalex.org/W3045196480","https://openalex.org/W3083550439","https://openalex.org/W3090449556","https://openalex.org/W3092363664","https://openalex.org/W3102725307","https://openalex.org/W3109271037","https://openalex.org/W3133226919","https://openalex.org/W3147467731","https://openalex.org/W3173290664","https://openalex.org/W3175528717","https://openalex.org/W3203359574","https://openalex.org/W3204447181","https://openalex.org/W4312396348","https://openalex.org/W4312439137","https://openalex.org/W4312910375","https://openalex.org/W4382240684","https://openalex.org/W4385245566","https://openalex.org/W4386065518","https://openalex.org/W4386071548","https://openalex.org/W4386076650","https://openalex.org/W6682962330","https://openalex.org/W6734312481","https://openalex.org/W6755207826","https://openalex.org/W6784631112","https://openalex.org/W6790341964","https://openalex.org/W6846322403"],"related_works":["https://openalex.org/W4386159726","https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2082269393"],"abstract_inverted_index":{"Continuous":[0],"sign":[1,12,159],"language":[2,13,160],"recognition":[3],"(CSLR)":[4],"is":[5,24,51],"to":[6,40,110,205],"recognize":[7],"the":[8,16,47,87,92,99,112,131,145,164,174,181,184,207,211],"glosses":[9,35],"in":[10],"a":[11,25,54,62,70,104,117,128,141],"video.":[14],"Enhancing":[15],"generalization":[17,208],"ability":[18,209],"of":[19,28,91,130,144,176,180,210],"CSLR's":[20],"visual":[21,44,81,100,212],"feature":[22,50,75,82,97,101,114,213],"extractor":[23],"worthy":[26],"area":[27],"investigation.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,60],"model":[34,189],"as":[36,202],"priors":[37],"that":[38,163],"help":[39],"learn":[41],"more":[42],"generalizable":[43],"features.":[45],"Specifically,":[46],"signer-invariant":[48],"gloss":[49,56,63,96,187],"extracted":[52],"by":[53,127,139],"pre-trained":[55,95,186],"BERT":[57,188],"model.":[58],"Then":[59],"design":[61],"prior":[64],"guidance":[65],"network":[66],"(GPGN).":[67],"It":[68],"contains":[69],"novel":[71],"parallel":[72],"densely-connected":[73],"temporal":[74,89],"extraction":[76],"(PDC-TFE)":[77],"module":[78],"for":[79],"multi-resolution":[80],"extraction.":[83],"The":[84,94,134,152,170],"PDC-TFE":[85],"captures":[86],"complex":[88],"patterns":[90],"glosses.":[93],"guides":[98],"learning":[102],"through":[103],"cross-modality":[105,113,146,191],"matching":[106,115,147,192],"loss.":[107,151],"We":[108],"propose":[109],"formulate":[111],"into":[116,197],"regularized":[118],"optimal":[119],"transport":[120],"problem,":[121],"it":[122],"can":[123,193],"be":[124,194],"efficiently":[125],"solved":[126],"variant":[129],"Sinkhorn":[132],"algorithm.":[133],"GPGN":[135,166],"parameters":[136],"are":[137],"learned":[138],"optimizing":[140],"weighted":[142],"sum":[143],"loss":[148],"and":[149,157,190],"CTC":[150],"experiment":[153],"results":[154],"on":[155],"German":[156],"Chinese":[158],"benchmarks":[161],"demonstrate":[162],"proposed":[165,185],"achieves":[167],"competitive":[168],"performance.":[169],"ablation":[171],"study":[172],"verifies":[173],"effectiveness":[175],"several":[177],"critical":[178],"components":[179],"GPGN.":[182],"Furthermore,":[183],"seamlessly":[195],"integrated":[196],"other":[198],"RGB-cue-based":[199],"CSLR":[200],"methods":[201],"plug-and-play":[203],"formulations":[204],"enhance":[206],"extractor.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}