{"id":"https://openalex.org/W3205193540","doi":"https://doi.org/10.1109/tmm.2021.3115626","title":"CroMM-VSR: Cross-Modal Memory Augmented Visual Speech Recognition","display_name":"CroMM-VSR: Cross-Modal Memory Augmented Visual Speech Recognition","publication_year":2021,"publication_date":"2021-10-11","ids":{"openalex":"https://openalex.org/W3205193540","doi":"https://doi.org/10.1109/tmm.2021.3115626","mag":"3205193540"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3115626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3115626","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":"https://openalex.org/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6514-0018","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067120705","display_name":"Joanna Hong","orcid":"https://orcid.org/0000-0003-4182-1000"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joanna Hong","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4182-1000","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376688","display_name":"Se Jin Park","orcid":"https://orcid.org/0000-0001-8467-3576"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se Jin Park","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8467-3576","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":3.9039,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94473998,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"4342","last_page":"4355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8028618097305298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7203073501586914},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5585623979568481},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.4828405976295471},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46145710349082947},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44806352257728577},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.4102141857147217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3795183002948761},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2638108432292938},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.22245526313781738},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1525460183620453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028618097305298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7203073501586914},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5585623979568481},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.4828405976295471},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46145710349082947},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44806352257728577},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.4102141857147217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3795183002948761},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2638108432292938},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.22245526313781738},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1525460183620453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2021.3115626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3115626","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:koasas.kaist.ac.kr:10203/300263","is_oa":false,"landing_page_url":"http://hdl.handle.net/10203/300263","pdf_url":null,"source":{"id":"https://openalex.org/S4306402435","display_name":"KAIST Institutional Repository (KAIST)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157485424","host_organization_name":"Korea Advanced Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I157485424"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W1965555277","https://openalex.org/W1983364832","https://openalex.org/W2005227457","https://openalex.org/W2015143272","https://openalex.org/W2023507242","https://openalex.org/W2029199293","https://openalex.org/W2076462394","https://openalex.org/W2090479364","https://openalex.org/W2096263221","https://openalex.org/W2121486117","https://openalex.org/W2127141656","https://openalex.org/W2134867751","https://openalex.org/W2164450870","https://openalex.org/W2165698076","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2735529525","https://openalex.org/W2766219058","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2893436174","https://openalex.org/W2897492880","https://openalex.org/W2943455019","https://openalex.org/W2950864153","https://openalex.org/W2951008357","https://openalex.org/W2963030892","https://openalex.org/W2963448850","https://openalex.org/W2963526065","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963680240","https://openalex.org/W2963785710","https://openalex.org/W2964199361","https://openalex.org/W2964216321","https://openalex.org/W2966792645","https://openalex.org/W2981501041","https://openalex.org/W2996970093","https://openalex.org/W2997918867","https://openalex.org/W3007589762","https://openalex.org/W3015383493","https://openalex.org/W3015830103","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3086926995","https://openalex.org/W3099202502","https://openalex.org/W3103801904","https://openalex.org/W3127334095","https://openalex.org/W3127645834","https://openalex.org/W3128564814","https://openalex.org/W3128750130","https://openalex.org/W3162707322","https://openalex.org/W3181942264","https://openalex.org/W3202329597","https://openalex.org/W3203789665","https://openalex.org/W4298112588","https://openalex.org/W6638318767","https://openalex.org/W6638523607","https://openalex.org/W6732703391","https://openalex.org/W6732742072","https://openalex.org/W6732872814","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6751751081","https://openalex.org/W6763296340","https://openalex.org/W6767349417","https://openalex.org/W6776472420","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W90026711","https://openalex.org/W2539140714","https://openalex.org/W82246966","https://openalex.org/W2894997731","https://openalex.org/W2368779261","https://openalex.org/W180632291","https://openalex.org/W2083580856","https://openalex.org/W2263479716","https://openalex.org/W2321571402","https://openalex.org/W1591608209"],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"(VSR)":[3],"is":[4,30,39,54,81],"a":[5,85,113,158],"task":[6],"that":[7,87,224],"recognizes":[8],"speech":[9,63,93],"from":[10,25],"external":[11],"appearances":[12],"of":[13,43,107,131,154,199],"the":[14,23,26,36,44,66,104,128,135,142,146,162,169,181,187,191,197,200,206,215,225,241,245],"face":[15],"(${\\it":[16],"i}.{\\it":[17],"e}.$,":[18],"lips)":[19],"into":[20,157],"text.":[21],"Since":[22],"information":[24,61,68,91,105,130,212,249],"visual":[27,96,108,164,218],"lip":[28,109],"movements":[29],"not":[31,70,139],"sufficient":[32],"to":[33,50,83,126,150,185,195],"fully":[34],"represent":[35],"speech,":[37],"VSR":[38,117],"considered":[40],"as":[41,75],"one":[42],"challenging":[45],"problems.":[46],"One":[47],"possible":[48],"way":[49,86],"resolve":[51],"this":[52,100,167],"problem":[53],"additionally":[55],"utilizing":[56],"audio":[57,67,132,136,152,177,182,188,211],"which":[58],"contains":[59,171],"rich":[60,210],"for":[62,92,250],"recognition.":[64],"However,":[65],"could":[69],"be":[71],"always":[72],"available":[73],"such":[74],"in":[76],"crowded":[77],"situations.":[78],"Thus,":[79],"it":[80],"necessary":[82],"find":[84],"successfully":[88],"provides":[89],"enough":[90],"recognition":[94],"with":[95,118],"inputs":[97,137,219],"only.":[98,220],"In":[99,237],"paper,":[101],"we":[102,239],"alleviate":[103],"insufficiency":[106],"movement":[110],"by":[111,213],"proposing":[112],"cross-modal":[114],"memory":[115,159,184,194,216],"augmented":[116],"Visual-Audio":[119],"Memory":[120],"(VAM).":[121],"The":[122],"proposed":[123,147,226],"framework":[124],"tries":[125],"utilize":[127],"complementary":[129],"even":[133],"when":[134],"are":[138],"provided":[140],"at":[141],"inference":[143],"time.":[144],"Concretely,":[145],"VAM":[148,170,207,246],"learns":[149],"imprint":[151,186],"features":[153],"short":[155],"clip-level":[156],"network":[160],"using":[161,217],"corresponding":[163],"features.":[165],"To":[166],"end,":[168],"two":[172],"memories,":[173],"lip-video":[174,192],"key":[175,193],"and":[176,190,234],"value.":[178],"We":[179],"guide":[180],"value":[183],"feature":[189],"memorize":[196],"location":[198],"imprinted":[201],"audio.":[202],"By":[203],"doing":[204],"this,":[205],"can":[208],"exploit":[209],"accessing":[214],"Experimental":[221],"results":[222],"show":[223],"method":[227],"achieves":[228],"state-of-the-art":[229],"performance":[230],"on":[231],"both":[232],"word-":[233],"sentence-level":[235],"VSR.":[236,251],"addition,":[238],"verify":[240],"learned":[242],"representations":[243],"inside":[244],"contain":[247],"meaningful":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}