{"id":"https://openalex.org/W3207505152","doi":"https://doi.org/10.1109/tmm.2021.3118287","title":"Audio-Driven Talking Video Frame Restoration","display_name":"Audio-Driven Talking Video Frame Restoration","publication_year":2021,"publication_date":"2021-10-10","ids":{"openalex":"https://openalex.org/W3207505152","doi":"https://doi.org/10.1109/tmm.2021.3118287","mag":"3207505152"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3118287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3118287","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/A5059602960","display_name":"Harry H. Cheng","orcid":"https://orcid.org/0000-0001-7436-0162"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Harry Cheng","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-7436-0162","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054313646","display_name":"Yangyang Guo","orcid":"https://orcid.org/0000-0001-8691-5372"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Guo","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8691-5372","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianhua Yin","orcid":"https://orcid.org/0000-0002-4611-2986"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Yin","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-4611-2986","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767769","display_name":"Haonan Chen","orcid":"https://orcid.org/0000-0001-8885-5051"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Chen","raw_affiliation_strings":["Tmall Genie-AI, Alibaba Cloud Intelligence Business Group, Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tmall Genie-AI, Alibaba Cloud Intelligence Business Group, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076920776","display_name":"Jiafang Wang","orcid":"https://orcid.org/0000-0003-1235-153X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafang Wang","raw_affiliation_strings":["Tmall Genie-AI, Alibaba Cloud Intelligence Business Group, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1235-153X","affiliations":[{"raw_affiliation_string":"Tmall Genie-AI, Alibaba Cloud Intelligence Business Group, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059602960"],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":1.2337,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.79796628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"4110","last_page":"4122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9983999729156494,"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":0.8624298572540283},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6320967674255371},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5215896964073181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48538219928741455},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4533296823501587},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.45258861780166626},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.45062899589538574},{"id":"https://openalex.org/keywords/inter-frame","display_name":"Inter frame","score":0.4468918740749359},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4073391556739807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38237452507019043},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3636016845703125},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.3540436625480652},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.30276983976364136},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10453745722770691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8624298572540283},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6320967674255371},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5215896964073181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48538219928741455},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4533296823501587},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.45258861780166626},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.45062899589538574},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.4468918740749359},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4073391556739807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38237452507019043},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3636016845703125},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3540436625480652},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.30276983976364136},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10453745722770691},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3118287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3118287","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G2053485949","display_name":null,"funder_award_id":"ZR2019JQ23","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G5596734660","display_name":null,"funder_award_id":"61802231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8886733673","display_name":null,"funder_award_id":"ZR2019QF001","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1901129140","https://openalex.org/W2111110632","https://openalex.org/W2114336453","https://openalex.org/W2133665775","https://openalex.org/W2348664362","https://openalex.org/W2586480386","https://openalex.org/W2594690981","https://openalex.org/W2808631503","https://openalex.org/W2922023437","https://openalex.org/W2944294033","https://openalex.org/W2944668088","https://openalex.org/W2949258649","https://openalex.org/W2950864153","https://openalex.org/W2963093735","https://openalex.org/W2963115079","https://openalex.org/W2963173190","https://openalex.org/W2963268050","https://openalex.org/W2963290645","https://openalex.org/W2963775347","https://openalex.org/W2963887950","https://openalex.org/W2981767644","https://openalex.org/W2990452356","https://openalex.org/W2997150500","https://openalex.org/W2997992233","https://openalex.org/W3010003739","https://openalex.org/W3015734344","https://openalex.org/W3016663370","https://openalex.org/W3020895012","https://openalex.org/W3021962567","https://openalex.org/W3034211329","https://openalex.org/W3034921716","https://openalex.org/W3081492798","https://openalex.org/W3087121792","https://openalex.org/W3092954151","https://openalex.org/W3099505600","https://openalex.org/W3101631197","https://openalex.org/W3105763085","https://openalex.org/W3116298410","https://openalex.org/W3186090335","https://openalex.org/W3192587235","https://openalex.org/W4312623579","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6767201353","https://openalex.org/W6767264202"],"related_works":["https://openalex.org/W2120864667","https://openalex.org/W2120898383","https://openalex.org/W2117554142","https://openalex.org/W2367517378","https://openalex.org/W2981480840","https://openalex.org/W2045735464","https://openalex.org/W1505485478","https://openalex.org/W3147815861","https://openalex.org/W2039403529","https://openalex.org/W2156008990"],"abstract_inverted_index":{"Talking":[0,143],"video":[1,84,93,102,124,153],"frames":[2,26,49,94,156],"occasionally":[3],"drop":[4,67],"while":[5],"streaming":[6],"for":[7,59,148],"reasons":[8],"like":[9],"network":[10,117],"errors,":[11],"which":[12],"greatly":[13],"hurts":[14],"the":[15,24,28,53,79,98,105,119,131],"online":[16],"team":[17],"collaboration":[18],"and":[19,41,62,100,128,154,165],"user":[20],"experiences.":[21],"Directly":[22],"generating":[23],"dropped":[25,92,132],"from":[27],"remaining":[29,101],"ones":[30],"is":[31,38,63],"unfavorable":[32],"since":[33],"a":[34,111,140],"person\u2019s":[35],"lip":[36,60],"motion":[37,61],"usually":[39],"non-linear":[40],"thus":[42],"hard":[43],"to":[44,66,180],"be":[45],"restored":[46],"when":[47],"consecutive":[48],"are":[50],"missing.":[51],"Nevertheless,":[52],"audio":[54,99,121],"content":[55,122],"provides":[56],"strong":[57],"signals":[58],"less":[64],"likely":[65],"during":[68],"transmitting.":[69],"Inspired":[70],"by":[71,95],"this,":[72],"as":[73,178],"an":[74],"initial":[75],"attempt,":[76],"we":[77,109,138],"present":[78],"task":[80],"of":[81,151],"audio-driven":[82],"talking":[83],"frame":[85,107,113],"restoration":[86,114],"in":[87,157],"this":[88],"paper,":[89],"i.e.,":[90],"restoring":[91],"jointly":[96],"leveraging":[97],"frames.":[103,133],"Towards":[104],"high-quality":[106],"generation,":[108],"devise":[110],"cross-modal":[112],"network.":[115],"This":[116],"aligns":[118],"complete":[120],"with":[123],"frames,":[125],"precisely":[126],"identifies":[127],"sequentially":[129],"generates":[130],"To":[134],"justify":[135],"our":[136],"model,":[137],"construct":[139],"new":[141],"dataset,":[142],"Video":[144],"Frames":[145],"Drop,":[146],"TVFD":[147,164],"short,":[149],"consisting":[150],"2.5K":[152],"144K":[155],"total.":[158],"We":[159],"conduct":[160],"extensive":[161],"experiments":[162],"over":[163],"another":[166],"publicly":[167],"accessible":[168],"dataset":[169],"-":[170],"Voxceleb2.":[171],"Our":[172],"model":[173],"obtains":[174],"significantly":[175],"improved":[176],"performance":[177],"compared":[179],"other":[181],"state-of-the-art":[182],"competitors.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
