{"id":"https://openalex.org/W4236398794","doi":"https://doi.org/10.1109/tmm.2021.3102433","title":"Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading","display_name":"Adaptive Semantic-Spatio-Temporal Graph Convolutional Network for Lip Reading","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W4236398794","doi":"https://doi.org/10.1109/tmm.2021.3102433"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3102433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3102433","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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":null,"display_name":"Changchong Sheng","orcid":"https://orcid.org/0000-0002-7842-2583"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Changchong Sheng","raw_affiliation_strings":["College of Electronic Science, National University of Defense Technology, Changsha, China","Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7842-2583","affiliations":[{"raw_affiliation_string":"College of Electronic Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671239","display_name":"Xinzhong Zhu","orcid":"https://orcid.org/0000-0002-0033-5260"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhong Zhu","raw_affiliation_strings":["Research Institute of Ningbo Cixing Company Ltd., Ningbo, China","College of Mathematics, Physics, and Information Engineering, Zhejiang Normal University, Jinhua, China"],"raw_orcid":"https://orcid.org/0000-0002-0033-5260","affiliations":[{"raw_affiliation_string":"Research Institute of Ningbo Cixing Company Ltd., Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"College of Mathematics, Physics, and Information Engineering, Zhejiang Normal University, Jinhua, China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080753121","display_name":"Huiying Xu","orcid":"https://orcid.org/0000-0002-6704-0301"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiying Xu","raw_affiliation_strings":["Research Institute of Ningbo Cixing Company Ltd., Ningbo, China","College of Mathematics, and Computer Science, Zhejiang Normal University, Jinhua, China"],"raw_orcid":"https://orcid.org/0000-0002-6704-0301","affiliations":[{"raw_affiliation_string":"Research Institute of Ningbo Cixing Company Ltd., Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"College of Mathematics, and Computer Science, Zhejiang Normal University, Jinhua, China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014611768","display_name":"Matti Pietik\u00e4inen","orcid":"https://orcid.org/0000-0003-2263-6731"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matti Pietikainen","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2263-6731","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-2011-2873","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9943,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92326406,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"3545","last_page":"3557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9704999923706055,"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":0.8778609037399292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6180638670921326},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5530864000320435},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5173365473747253},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4923588037490845},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4698810875415802},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4177819788455963},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3770105540752411},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3669915199279785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14529478549957275},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.0845775306224823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8778609037399292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6180638670921326},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5530864000320435},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5173365473747253},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4923588037490845},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4698810875415802},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4177819788455963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3770105540752411},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3669915199279785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14529478549957275},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0845775306224823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2021.3102433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3102433","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:oulu.fi:nbnfi-fe2022100661272","is_oa":false,"landing_page_url":"http://urn.fi/urn:nbn:fi-fe2022100661272","pdf_url":null,"source":{"id":"https://openalex.org/S4306400284","display_name":"University of Oulu Repository (University of Oulu)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98381234","host_organization_name":"University of Oulu","host_organization_lineage":["https://openalex.org/I98381234"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8899999856948853}],"awards":[{"id":"https://openalex.org/G1767751821","display_name":null,"funder_award_id":"2018R51001","funder_id":"https://openalex.org/F4320329747","funder_display_name":"Zhejiang Provincial Ten Thousand Plan for Young Top Talents"},{"id":"https://openalex.org/G2443591357","display_name":"LESLearn: Label, Energy and Sample Efficient Feature Representation and Learning in Computer Vision","funder_award_id":"331883","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G4333678435","display_name":null,"funder_award_id":"61976196","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8008312880","display_name":null,"funder_award_id":"331883","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320329747","display_name":"Zhejiang Provincial Ten Thousand Plan for Young Top Talents","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W637153065","https://openalex.org/W2005227457","https://openalex.org/W2033895145","https://openalex.org/W2087681821","https://openalex.org/W2098355375","https://openalex.org/W2102443632","https://openalex.org/W2113814270","https://openalex.org/W2127141656","https://openalex.org/W2136155248","https://openalex.org/W2138527036","https://openalex.org/W2144513380","https://openalex.org/W2163973301","https://openalex.org/W2194775991","https://openalex.org/W2398406965","https://openalex.org/W2408589826","https://openalex.org/W2471768434","https://openalex.org/W2551572271","https://openalex.org/W2558460151","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2613448434","https://openalex.org/W2787613668","https://openalex.org/W2798734012","https://openalex.org/W2799930024","https://openalex.org/W2886945201","https://openalex.org/W2888096830","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2897492880","https://openalex.org/W2948058585","https://openalex.org/W2949662773","https://openalex.org/W2950864153","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963017945","https://openalex.org/W2963066677","https://openalex.org/W2963076818","https://openalex.org/W2963084622","https://openalex.org/W2963091558","https://openalex.org/W2963115079","https://openalex.org/W2963524571","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963656031","https://openalex.org/W2964015378","https://openalex.org/W2964283370","https://openalex.org/W2972756321","https://openalex.org/W2981501041","https://openalex.org/W2981851635","https://openalex.org/W2986953233","https://openalex.org/W2996249958","https://openalex.org/W3009224666","https://openalex.org/W3015830103","https://openalex.org/W3016011581","https://openalex.org/W3017343282","https://openalex.org/W3023351797","https://openalex.org/W3034230284","https://openalex.org/W3046890131","https://openalex.org/W3092336341","https://openalex.org/W3104792420","https://openalex.org/W3108240585","https://openalex.org/W3122663073","https://openalex.org/W4231077848","https://openalex.org/W4298112588","https://openalex.org/W6620673361","https://openalex.org/W6631751486","https://openalex.org/W6679436768","https://openalex.org/W6685350579","https://openalex.org/W6713582119","https://openalex.org/W6719270105","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6732872814","https://openalex.org/W6736685754","https://openalex.org/W6738964360","https://openalex.org/W6739901393","https://openalex.org/W6748320467","https://openalex.org/W6754420807","https://openalex.org/W6763296340"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,38,49,75,85,98],"this":[3,91],"work":[4],"is":[5,68,140],"to":[6,54,70,109],"recognize":[7],"words,":[8],"phrases,":[9],"and":[10,34,56,87,120,132],"sentences":[11],"being":[12],"spoken":[13],"by":[14,114],"a":[15,95,135],"talking":[16],"face":[17],"without":[18],"given":[19],"the":[20,32,47,59,73,118,127,146,151],"audio.":[21],"Current":[22],"deep":[23],"learning":[24,116],"approaches":[25],"for":[26],"lip":[27,50,153,159],"reading":[28,154,160],"focus":[29],"on":[30,156],"exploring":[31],"appearance":[33,55,86,131],"optical":[35,57,88],"flow":[36],"information":[37,66,122,129],"videos.":[39,124],"However,":[40,72],"these":[41],"methods":[42,113,155],"do":[43],"not":[44],"fully":[45],"exploit":[46],"characteristics":[48],"motion.":[51],"In":[52,90],"addition":[53],"flow,":[58],"mouth":[60,77,100,133],"contour":[61,78],"deformation":[62],"usually":[63],"conveys":[64],"significant":[65],"that":[67,84,145],"complementary":[69,128],"others.":[71],"modeling":[74],"dynamic":[76,99],"has":[79],"received":[80],"little":[81],"attention":[82],"than":[83],"flow.":[89],"work,":[92],"we":[93],"propose":[94],"novel":[96],"model":[97],"contours":[101],"called":[102],"Adaptive":[103],"Semantic-Spatio-Temporal":[104],"Graph":[105],"Convolution":[106],"Network":[107],"(ASST-GCN),":[108],"go":[110],"beyond":[111],"previous":[112],"automatically":[115],"both":[117],"spatial":[119],"temporal":[121],"from":[123,130],"To":[125],"combine":[126],"contour,":[134],"two-stream":[136],"visual":[137],"front-end":[138],"network":[139],"proposed.":[141],"Experimental":[142],"results":[143],"demonstrate":[144],"proposed":[147],"method":[148],"significantly":[149],"outperforms":[150],"state-of-the-art":[152],"several":[157],"large-scale":[158],"benchmarks.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}