{"id":"https://openalex.org/W4392902820","doi":"https://doi.org/10.1109/icassp48485.2024.10445887","title":"VK-G2T: Vision and Context Knowledge Enhanced Gloss2text","display_name":"VK-G2T: Vision and Context Knowledge Enhanced Gloss2text","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902820","doi":"https://doi.org/10.1109/icassp48485.2024.10445887"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445887","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5051341911","display_name":"Liqiang Jing","orcid":"https://orcid.org/0000-0001-9827-5835"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liqiang Jing","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072768866","display_name":"Xuemeng Song","orcid":"https://orcid.org/0000-0002-5274-4197"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemeng Song","raw_affiliation_strings":["Shandong University"],"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028097242","display_name":"Xinxing Zu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinxing Zu","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110367814","display_name":"Na Zheng","orcid":null},"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":"Na Zheng","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058996194","display_name":"Zhongzhou Zhao","orcid":"https://orcid.org/0000-0002-3519-6301"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongzhou Zhao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5051341911"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02542264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7860","last_page":"7864"},"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9896000027656555,"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":0.9830999970436096,"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/gloss","display_name":"Gloss (optics)","score":0.9367011785507202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7710745930671692},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6129227876663208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5462467670440674},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5067797303199768},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5025734901428223},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4903836250305176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.325130820274353},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2151373028755188}],"concepts":[{"id":"https://openalex.org/C143025027","wikidata":"https://www.wikidata.org/wiki/Q900581","display_name":"Gloss (optics)","level":3,"score":0.9367011785507202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710745930671692},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6129227876663208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462467670440674},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5067797303199768},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5025734901428223},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4903836250305176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.325130820274353},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2151373028755188},{"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/C2781448156","wikidata":"https://www.wikidata.org/wiki/Q1570182","display_name":"Coating","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445887","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":18,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2799020610","https://openalex.org/W2908497602","https://openalex.org/W3001434439","https://openalex.org/W3016918797","https://openalex.org/W3034765865","https://openalex.org/W3034999214","https://openalex.org/W3114337930","https://openalex.org/W3147467731","https://openalex.org/W3173290664","https://openalex.org/W4213009331","https://openalex.org/W4285119160","https://openalex.org/W4312396348","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6682631176"],"related_works":["https://openalex.org/W3119463769","https://openalex.org/W2035926194","https://openalex.org/W2514360315","https://openalex.org/W2045489541","https://openalex.org/W2134811186","https://openalex.org/W2160360150","https://openalex.org/W1985904311","https://openalex.org/W4247897165","https://openalex.org/W2358737221","https://openalex.org/W2040681928"],"abstract_inverted_index":{"Existing":[0],"sign":[1,12,100],"language":[2,13,31,101],"translation":[3,120],"methods":[4],"follow":[5],"a":[6,16,29,83,128],"two-stage":[7],"pipeline:":[8],"first":[9],"converting":[10],"the":[11,24,42,45,50,53,95,99,105,108,113,118,132],"video":[14,102],"to":[15,62,103,116],"gloss":[17,26,70,75,122],"sequence":[18,27],"(i.e.,":[19,33],"Sign2Gloss)":[20],"and":[21,72,85,111],"then":[22],"translating":[23],"generated":[25],"into":[28],"spoken":[30],"sentence":[32,110],"Gloss2Text).":[34],"While":[35],"previous":[36],"studies":[37],"have":[38],"focused":[39],"on":[40,127],"boosting":[41],"performance":[43],"of":[44,52,66,98,107,121,134],"Sign2Gloss":[46],"stage,":[47],"we":[48,81],"emphasize":[49],"optimization":[51],"Gloss2Text":[54,89],"stage.":[55],"However,":[56],"this":[57],"task":[58],"is":[59],"non-trivial":[60],"due":[61],"two":[63],"distinct":[64],"features":[65],"Gloss2Text:":[67],"(1)":[68],"isolated":[69],"input":[71],"(2)":[73],"low-capacity":[74],"vocabulary.":[76],"To":[77],"address":[78],"these":[79],"issues,":[80],"propose":[82],"vision":[84],"context":[86,114],"knowledge":[87,115],"enhanced":[88],"model,":[90],"named":[91],"VK-G2T,":[92],"which":[93],"leverages":[94],"visual":[96],"content":[97],"learn":[104],"properties":[106],"target":[109],"exploit":[112],"facilitate":[117],"adaptive":[119],"words.":[123],"Extensive":[124],"experiments":[125],"conducted":[126],"Chinese":[129],"benchmark":[130],"validate":[131],"superiority":[133],"our":[135],"model.":[136]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
