{"id":"https://openalex.org/W3015689952","doi":"https://doi.org/10.1109/icassp40776.2020.9054384","title":"Towards Pose-Invariant Lip-Reading","display_name":"Towards Pose-Invariant Lip-Reading","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015689952","doi":"https://doi.org/10.1109/icassp40776.2020.9054384","mag":"3015689952"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5017072420","display_name":"Shiyang Cheng","orcid":"https://orcid.org/0000-0003-1932-7823"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shiyang Cheng","raw_affiliation_strings":["Imperial College, London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Imperial College, London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024224610","display_name":"Georgios Tzimiropoulos","orcid":"https://orcid.org/0000-0002-1803-5338"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Tzimiropoulos","raw_affiliation_strings":["University of Nottingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Imperial College, London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072822225","display_name":"Adrian Bulat","orcid":"https://orcid.org/0000-0002-3185-4979"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrian Bulat","raw_affiliation_strings":["Samsung AI Center, Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center, Cambridge","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101405147","display_name":"Jie Shen","orcid":"https://orcid.org/0000-0002-6722-2754"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Shen","raw_affiliation_strings":["Imperial College, London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Imperial College, London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7373,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91018784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4357","last_page":"4361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T13289","display_name":"Infant Health and Development","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7813268899917603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6749421954154968},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5087650418281555},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4984416961669922},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4828124940395355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4275953471660614},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42464056611061096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37593063712120056},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3595811128616333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32952362298965454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07313475012779236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813268899917603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6749421954154968},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5087650418281555},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4984416961669922},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4828124940395355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4275953471660614},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42464056611061096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37593063712120056},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3595811128616333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32952362298965454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07313475012779236},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W196088823","https://openalex.org/W1522301498","https://openalex.org/W1535545184","https://openalex.org/W1588214556","https://openalex.org/W1590203237","https://openalex.org/W1935685005","https://openalex.org/W2017107803","https://openalex.org/W2078711706","https://openalex.org/W2107037917","https://openalex.org/W2160126058","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2265959009","https://openalex.org/W2267805933","https://openalex.org/W2304348237","https://openalex.org/W2404704342","https://openalex.org/W2406846463","https://openalex.org/W2551572271","https://openalex.org/W2578229578","https://openalex.org/W2594690981","https://openalex.org/W2753407461","https://openalex.org/W2772024431","https://openalex.org/W2890952074","https://openalex.org/W2893436174","https://openalex.org/W2914859359","https://openalex.org/W2949662773","https://openalex.org/W2952746495","https://openalex.org/W2962912639","https://openalex.org/W2963192365","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2964121744","https://openalex.org/W3104792420","https://openalex.org/W4298112588","https://openalex.org/W6607899525","https://openalex.org/W6631190155","https://openalex.org/W6635250320","https://openalex.org/W6640455264","https://openalex.org/W6654799313","https://openalex.org/W6686207219","https://openalex.org/W6713551954","https://openalex.org/W6732872814","https://openalex.org/W6734491695","https://openalex.org/W6734790163","https://openalex.org/W6743738265","https://openalex.org/W6743905813","https://openalex.org/W6746191961","https://openalex.org/W6754392867","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W2082438799","https://openalex.org/W1966986837","https://openalex.org/W2360138227","https://openalex.org/W4365808155","https://openalex.org/W1838455177","https://openalex.org/W1489909378","https://openalex.org/W2392697679","https://openalex.org/W2385990477","https://openalex.org/W2331964906","https://openalex.org/W2067734110"],"abstract_inverted_index":{"Lip-reading":[0],"models":[1,48],"have":[2],"been":[3],"significantly":[4,67],"improved":[5],"recently":[6],"thanks":[7],"to":[8,89,96,120,165],"powerful":[9],"deep":[10],"learning":[11],"architectures.":[12],"However,":[13],"most":[14],"works":[15],"focused":[16],"on":[17,49,71,79,137],"frontal":[18,21,80,83,104],"or":[19],"near":[20,82],"views":[22,73],"of":[23,53,146,150,163],"the":[24,76,138,151,168],"mouth.":[25],"As":[26],"a":[27,42,91,122,130],"consequence,":[28],"lip-reading":[29,47],"performance":[30,78],"seriously":[31],"deteriorates":[32],"in":[33,111,156],"non-frontal":[34,57,72],"mouth":[35,84],"views.":[36,85],"In":[37],"this":[38],"work,":[39],"we":[40,87],"present":[41],"framework":[43],"for":[44,126,133],"training":[45],"pose-invariant":[46],"synthetic":[50,108],"data":[51,58,110],"instead":[52],"collecting":[54],"and":[55,62,81,141],"annotating":[56],"which":[59],"is":[60,118,170],"costly":[61],"tedious.":[63],"The":[64,114,148],"proposed":[65,152],"model":[66],"outperforms":[68],"previous":[69],"approaches":[70],"while":[74],"retaining":[75],"superior":[77],"Specifically,":[86],"propose":[88],"use":[90],"3D":[92],"Morphable":[93],"Model":[94],"(3DMM)":[95],"augment":[97],"LRW,":[98],"an":[99,143,160],"existing":[100],"large-scale":[101],"but":[102],"mostly":[103],"dataset,":[105,117,140],"by":[106],"generating":[107],"facial":[109],"arbitrary":[112],"poses.":[113],"newly":[115],"derived":[116],"used":[119],"train":[121],"state-of-the-art":[123],"neural":[124],"network":[125],"lip-reading.":[127],"We":[128],"conducted":[129],"cross-database":[131],"experiment":[132],"isolated":[134],"word":[135],"recognition":[136],"LRS2":[139],"reported":[142],"absolute":[144,161],"improvement":[145,162],"2.55%.":[147],"benefit":[149],"approach":[153],"becomes":[154],"clearer":[155],"extreme":[157],"poses":[158],"where":[159],"up":[164],"20.64%":[166],"over":[167],"baseline":[169],"achieved.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}