{"id":"https://openalex.org/W3093337631","doi":"https://doi.org/10.1145/3394171.3413740","title":"FastLR","display_name":"FastLR","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093337631","doi":"https://doi.org/10.1145/3394171.3413740","mag":"3093337631"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5065126806","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0002-9905-3887"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinglin Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374104","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-3944-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020858666","display_name":"Baoxing Huai","orcid":"https://orcid.org/0000-0001-9625-2314"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoxing Huai","raw_affiliation_strings":["HUAWEI TECHNOLOGIES CO., LTD., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"HUAWEI TECHNOLOGIES CO., LTD., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007552078","display_name":"Jing Yuan","orcid":"https://orcid.org/0000-0001-9178-3896"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yuan","raw_affiliation_strings":["Huawei Cloud BU, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud BU, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065126806"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.9829,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78773452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4328","last_page":"4336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9980999827384949,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9977999925613403,"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":0.8071532249450684},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7788525819778442},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5985081195831299},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5456169843673706},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4918956756591797},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48888128995895386},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4752086102962494},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.45439958572387695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45201051235198975},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44618314504623413},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.442979097366333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43787726759910583},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.43064698576927185},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41206222772598267},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.344965398311615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09388050436973572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071532249450684},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7788525819778442},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5985081195831299},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5456169843673706},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4918956756591797},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48888128995895386},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4752086102962494},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.45439958572387695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45201051235198975},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44618314504623413},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.442979097366333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43787726759910583},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43064698576927185},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41206222772598267},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.344965398311615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09388050436973572},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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":29,"referenced_works":["https://openalex.org/W1816313093","https://openalex.org/W1924770834","https://openalex.org/W2015143272","https://openalex.org/W2109596721","https://openalex.org/W2127141656","https://openalex.org/W2267805933","https://openalex.org/W2551572271","https://openalex.org/W2734984521","https://openalex.org/W2767206889","https://openalex.org/W2769810959","https://openalex.org/W2890952074","https://openalex.org/W2893436174","https://openalex.org/W2949888546","https://openalex.org/W2952746495","https://openalex.org/W2962969034","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2963528589","https://openalex.org/W2963536265","https://openalex.org/W2963785710","https://openalex.org/W2964283370","https://openalex.org/W2970832665","https://openalex.org/W2972756321","https://openalex.org/W2988975212","https://openalex.org/W2989134874","https://openalex.org/W2991061108","https://openalex.org/W3033411150","https://openalex.org/W3034363136","https://openalex.org/W3035490389"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W121858127","https://openalex.org/W2171218219"],"abstract_inverted_index":{"Lipreading":[0],"is":[1,61],"an":[2,192,215],"impressive":[3],"technique":[4],"and":[5,35,77,129,158,166,181,205,241,271,275],"there":[6],"has":[7,66],"been":[8],"a":[9,48,62,106,233],"definite":[10],"improvement":[11],"of":[12,72,86,95,109,117,125,133,142,202,224,269,284],"accuracy":[13],"in":[14,145],"recent":[15],"years.":[16],"However,":[17],"existing":[18],"methods":[19,151],"for":[20,239],"lipreading":[21,51,60,262,277],"mainly":[22],"build":[23],"on":[24,273],"autoregressive":[25,217],"(AR)":[26],"model,":[27],"which":[28,53,103,280],"generate":[29],"target":[30,56,78,110],"tokens":[31,57],"one":[32,34],"by":[33],"suffer":[36],"from":[37],"high":[38],"inference":[39],"latency.":[40],"To":[41,186,227],"breakthrough":[42],"this":[43,146],"constraint,":[44],"we":[45,148,168,190,231],"propose":[46,232],"FastLR,":[47],"non-autoregressive":[49],"(NAR)":[50],"model":[52,136,174,263],"generates":[54],"all":[55],"simultaneously.":[58],"NAR":[59,96],"challenging":[63],"task":[64],"that":[65,251],"many":[67],"difficulties:":[68],"1)":[69,161],"the":[70,84,87,91,99,113,131,138,154,175,200,203,221,254,282],"discrepancy":[71],"sequence":[73],"lengths":[74],"between":[75,156,177],"source":[76,178],"makes":[79],"it":[80,207],"difficult":[81],"to":[82,105,123,152,162,173,199,219,257],"estimate":[83],"length":[85],"output":[88,182],"sequence;":[89],"2)":[90,185],"conditionally":[92],"independent":[93],"behavior":[94],"generation":[97],"lacks":[98],"correlation":[100],"across":[101],"time":[102],"leads":[104],"poor":[107],"approximation":[108],"distribution;":[111],"3)":[112,226],"feature":[114,222],"representation":[115],"ability":[116],"encoder":[118,204],"can":[119],"be":[120],"weak":[121],"due":[122],"lack":[124],"effective":[126],"alignment":[127],"mechanism;":[128],"4)":[130],"removal":[132],"AR":[134,159],"language":[135],"exacerbates":[137],"inherent":[139],"ambiguity":[140],"problem":[141],"lipreading.":[143,247],"Thus,":[144],"paper,":[147],"introduce":[149],"three":[150],"reduce":[153],"gap":[155],"FastLR":[157,252],"model:":[160],"address":[163],"challenges":[164],"1":[165],"2,":[167],"leverage":[169],"integrate-and-fire":[170],"(I&F)":[171],"module":[172],"correspondence":[176],"video":[179],"frames":[180],"text":[183],"sequence.":[184],"tackle":[187],"challenge":[188,229],"3,":[189],"add":[191,214],"auxiliary":[193,216],"connectionist":[194],"temporal":[195],"classification":[196],"(CTC)":[197],"decoder":[198,218],"top":[201],"optimize":[206],"with":[208,260,264],"extra":[209],"CTC":[210],"loss.":[211],"We":[212],"also":[213],"help":[220],"extraction":[223],"encoder.":[225],"overcome":[228],"4,":[230],"novel":[234],"Noisy":[235],"Parallel":[236],"Decoding":[237],"(NPD)":[238],"I&F":[240],"bring":[242],"Byte-Pair":[243],"Encoding":[244],"(BPE)":[245],"into":[246],"Our":[248],"experiments":[249],"exhibit":[250],"achieves":[253],"speedup":[255],"up":[256],"10.97\u00d7":[258],"comparing":[259],"state-of-the-art":[261],"slight":[265],"WER":[266],"absolute":[267],"increase":[268],"1.5%":[270],"5.5%":[272],"GRID":[274],"LRS2":[276],"datasets":[278],"respectively,":[279],"demonstrates":[281],"effectiveness":[283],"our":[285],"proposed":[286],"method.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2020-10-22T00:00:00"}