{"id":"https://openalex.org/W4415545968","doi":"https://doi.org/10.1145/3728481.3762165","title":"Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource","display_name":"Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415545968","doi":"https://doi.org/10.1145/3728481.3762165"},"language":null,"primary_location":{"id":"doi:10.1145/3728481.3762165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728481.3762165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Multimodal Human Understanding for the Web and Social Media","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/A5102951734","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-7508-2341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7508-2341","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junshan Jin","orcid":"https://orcid.org/0009-0002-0860-6579"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junshan Jin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-0860-6579","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002005272","display_name":"Mingyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyuan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-3409-6947","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091670416","display_name":"Yi He","orcid":"https://orcid.org/0000-0002-2121-6076"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi He","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2121-6076","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063857788","display_name":"Bofan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bofan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-3241-6122","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717685","display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Lin Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8214-6809","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9954000115394592,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.8147000074386597},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5931000113487244},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5511000156402588},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4708000123500824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46219998598098755},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4399000108242035},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41839998960494995}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.8147000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7253000140190125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728481.3762165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3728481.3762165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Multimodal Human Understanding for the Web and Social Media","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2551572271","https://openalex.org/W2949662773","https://openalex.org/W2963192365","https://openalex.org/W2963566548","https://openalex.org/W3016011581","https://openalex.org/W3128564814","https://openalex.org/W3147719764","https://openalex.org/W4307286264","https://openalex.org/W4312444556","https://openalex.org/W4319300051","https://openalex.org/W4372346152","https://openalex.org/W4385194827","https://openalex.org/W4399039406","https://openalex.org/W4399423332"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"speech":[1,12],"recognition":[2],"is":[3,135,156],"a":[4,109,150],"technique":[5],"to":[6,122,137,158],"identify":[7],"spoken":[8],"content":[9],"in":[10,19,23,124],"silent":[11],"videos,":[13],"which":[14],"has":[15],"raised":[16],"significant":[17],"attention":[18],"recent":[20],"years.":[21],"Advancements":[22],"data-driven":[24],"deep":[25,40],"learning":[26,41],"methods":[27,42,79],"have":[28],"significantly":[29],"improved":[30],"both":[31],"the":[32,63,95,126,140,160,164,167,172,190],"speed":[33],"and":[34,55,87,100,143,187],"accuracy":[35,192],"of":[36,84,97,146,163],"recognition.":[37],"However,":[38],"these":[39,68,78],"can":[43],"be":[44],"effected":[45],"by":[46,67],"visual":[47,69,112,127,168],"disturbances,":[48],"such":[49],"as":[50,119],"lightning":[51],"conditions,":[52],"skin":[53],"texture":[54],"other":[56],"user-specific":[57,98],"features.":[58],"Data-driven":[59],"approaches":[60],"could":[61],"reduce":[62,94],"performance":[64,102],"degradation":[65],"caused":[66],"disturbances":[70],"using":[71],"models":[72],"pretrained":[73],"on":[74,193],"large-scale":[75],"datasets.":[76],"But":[77],"often":[80],"require":[81],"large":[82],"amounts":[83],"training":[85,125],"data":[86,186],"computational":[88],"resources,":[89],"making":[90],"them":[91],"costly.":[92],"To":[93],"influence":[96],"features":[99,145,162,169],"enhance":[101],"with":[103,166,184],"limited":[104,185],"data,":[105],"this":[106,180],"paper":[107],"proposed":[108],"landmark":[110],"guided":[111],"feature":[113,128],"extractor.":[114,129],"Facial":[115],"landmarks":[116,165],"are":[117],"used":[118],"auxiliary":[120],"information":[121],"aid":[123],"A":[130],"spatio-temporal":[131,144,161],"multi-graph":[132],"convolutional":[133],"network":[134],"designed":[136],"fully":[138],"exploit":[139],"spatial":[141],"locations":[142],"facial":[147],"landmarks.":[148],"Additionally,":[149],"multi-level":[151],"lip":[152],"dynamic":[153],"fusion":[154],"framework":[155],"introduced":[157],"combine":[159],"extracted":[170],"from":[171],"raw":[173],"video":[174],"frames.":[175],"Experimental":[176],"results":[177],"show":[178],"that":[179],"approach":[181],"performs":[182],"well":[183],"also":[188],"improves":[189],"model's":[191],"unseen":[194],"speakers.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}