{"id":"https://openalex.org/W4407774822","doi":"https://doi.org/10.1145/3711129.3711207","title":"Research on Tibetan Lip-Reading Recognition Methods Based on Attention Mechanisms","display_name":"Research on Tibetan Lip-Reading Recognition Methods Based on Attention Mechanisms","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4407774822","doi":"https://doi.org/10.1145/3711129.3711207"},"language":"en","primary_location":{"id":"doi:10.1145/3711129.3711207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711129.3711207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering","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/A5019397362","display_name":"Yuqing Cai","orcid":"https://orcid.org/0009-0000-0602-6816"},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Cai","raw_affiliation_strings":["Tibet University, Lhasa, Tibet, China"],"raw_orcid":"https://orcid.org/0009-0000-0602-6816","affiliations":[{"raw_affiliation_string":"Tibet University, Lhasa, Tibet, China","institution_ids":["https://openalex.org/I140786321"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-2714-9759"},"institutions":[{"id":"https://openalex.org/I20616075","display_name":"Qinghai Normal University","ror":"https://ror.org/03az1t892","country_code":"CN","type":"education","lineage":["https://openalex.org/I20616075"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Qinghai Normal University, Xining, Qinghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2714-9759","affiliations":[{"raw_affiliation_string":"Qinghai Normal University, Xining, Qinghai, China","institution_ids":["https://openalex.org/I20616075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116343092","display_name":"Lhamao Kji","orcid":null},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lhamao Kji","raw_affiliation_strings":["Tibet University, Lhasa, Tibet, China"],"raw_orcid":"https://orcid.org/0009-0009-6320-3001","affiliations":[{"raw_affiliation_string":"Tibet University, Lhasa, Tibet, China","institution_ids":["https://openalex.org/I140786321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057447308","display_name":"Renzeng Duojie","orcid":null},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renzeng Duojie","raw_affiliation_strings":["Tibet University, Lhasa, Tibet, China"],"raw_orcid":"https://orcid.org/0009-0008-3063-2443","affiliations":[{"raw_affiliation_string":"Tibet University, Lhasa, Tibet, China","institution_ids":["https://openalex.org/I140786321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021750037","display_name":"Yulei Zhu","orcid":"https://orcid.org/0009-0001-4812-7196"},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulei Zhu","raw_affiliation_strings":["Tibet University, Lhasa, Tibet, China"],"raw_orcid":"https://orcid.org/0009-0001-4812-7196","affiliations":[{"raw_affiliation_string":"Tibet University, Lhasa, Tibet, China","institution_ids":["https://openalex.org/I140786321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050819315","display_name":"Nyima Tashi","orcid":"https://orcid.org/0000-0001-9288-6600"},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nima Tashi","raw_affiliation_strings":["Tibet University, Lhasa, Tibet, China"],"raw_orcid":"https://orcid.org/0000-0001-9288-6600","affiliations":[{"raw_affiliation_string":"Tibet University, Lhasa, Tibet, China","institution_ids":["https://openalex.org/I140786321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.9941999912261963,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9521999955177307,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6787169575691223},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6376122832298279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34771186113357544},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1731669306755066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6787169575691223},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6376122832298279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34771186113357544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1731669306755066},{"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:10.1145/3711129.3711207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711129.3711207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2788241093","https://openalex.org/W2898420460","https://openalex.org/W2963163009","https://openalex.org/W2964121744","https://openalex.org/W3001079424","https://openalex.org/W3136428570","https://openalex.org/W4297775537","https://openalex.org/W4407354353","https://openalex.org/W6606547925"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"response":[1],"to":[2,13,69,82,98,130],"the":[3,20,62,105,112,123,131],"scarcity":[4],"of":[5,22,26,120],"Tibetan":[6,39,53,132],"lip-reading":[7,40,54,133],"data":[8],"resources,":[9],"which":[10],"has":[11],"led":[12],"limited":[14],"research":[15],"in":[16,32,43],"this":[17,34],"area,":[18],"and":[19,86,103],"presence":[21],"a":[23,37,49,58,91,116],"large":[24],"number":[25],"homophones":[27],"with":[28],"different":[29],"written":[30],"forms":[31],"Tibetan,":[33],"paper":[35],"constructs":[36],"word-level":[38],"dataset,":[41,125],"MTLRW-50,":[42],"complex":[44],"scenarios.":[45],"Additionally,":[46],"it":[47],"proposes":[48],"ResNet-Attention-BiLSTM-based":[50],"approach":[51],"for":[52],"recognition.":[55],"First,":[56],"leveraging":[57],"transfer":[59],"learning":[60],"strategy,":[61],"pre-trained":[63],"ResNet-50":[64],"residual":[65],"network":[66,95],"is":[67,80,96],"employed":[68],"extract":[70],"deep":[71],"features":[72],"from":[73],"video":[74],"frames.":[75],"Second,":[76],"an":[77,127],"attention":[78],"mechanism":[79],"introduced":[81],"capture":[83,100],"contextual":[84],"information":[85],"reduce":[87],"visual":[88],"ambiguities.":[89],"Finally,":[90],"bidirectional":[92],"LSTM":[93],"(BiLSTM)":[94],"utilized":[97],"fully":[99],"temporal":[101],"dependencies":[102],"perform":[104],"final":[106],"classification.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"that":[111],"proposed":[113],"model":[114],"achieves":[115],"TOP-1":[117],"classification":[118],"accuracy":[119],"95.82%":[121],"on":[122],"MTLRW-50":[124],"providing":[126],"effective":[128],"solution":[129],"recognition":[134],"task.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}