{"id":"https://openalex.org/W4298050485","doi":"https://doi.org/10.1145/3503161.3548080","title":"Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors","display_name":"Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4298050485","doi":"https://doi.org/10.1145/3503161.3548080"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548080","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.08118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081130373","display_name":"Sindhu B Hegde","orcid":"https://orcid.org/0009-0005-2845-5570"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sindhu B. Hegde","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660270","display_name":"Rudrabha Mukhopadhyay","orcid":"https://orcid.org/0009-0000-6628-7065"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rudrabha Mukhopadhyay","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinay P. Namboodiri","raw_affiliation_strings":["University of Bath, Bath, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Bath, Bath, United Kingdom","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C.V. Jawahar","raw_affiliation_strings":["International Institute of Information Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081130373"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.0598,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27665011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6511","last_page":"6520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9965000152587891,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9962999820709229,"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/upsampling","display_name":"Upsampling","score":0.8560048341751099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8478056192398071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6161085367202759},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5894343852996826},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5709748268127441},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4670402407646179},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.44867491722106934},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4475739598274231},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.348747193813324},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.32077479362487793}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8560048341751099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478056192398071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6161085367202759},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5894343852996826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5709748268127441},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4670402407646179},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.44867491722106934},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4475739598274231},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.348747193813324},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32077479362487793},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548080","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.08118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.08118","pdf_url":"https://arxiv.org/pdf/2208.08118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.08118","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.08118","pdf_url":"https://arxiv.org/pdf/2208.08118","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W2006525872","https://openalex.org/W2124964692","https://openalex.org/W2159680539","https://openalex.org/W2242218935","https://openalex.org/W2293468125","https://openalex.org/W2558333741","https://openalex.org/W2559655401","https://openalex.org/W2599705893","https://openalex.org/W2604379605","https://openalex.org/W2739757502","https://openalex.org/W2783348085","https://openalex.org/W2789010967","https://openalex.org/W2806833697","https://openalex.org/W2808631503","https://openalex.org/W2883102461","https://openalex.org/W2906447902","https://openalex.org/W2914217321","https://openalex.org/W2915130236","https://openalex.org/W2923834406","https://openalex.org/W2946215287","https://openalex.org/W2949662773","https://openalex.org/W2950864153","https://openalex.org/W2960274051","https://openalex.org/W2962918445","https://openalex.org/W2963093735","https://openalex.org/W2963307811","https://openalex.org/W2963372104","https://openalex.org/W2963729050","https://openalex.org/W2963887950","https://openalex.org/W2964171275","https://openalex.org/W2969834519","https://openalex.org/W2979157532","https://openalex.org/W2981856286","https://openalex.org/W2996880115","https://openalex.org/W3008823916","https://openalex.org/W3019952993","https://openalex.org/W3034352949","https://openalex.org/W3035195755","https://openalex.org/W3035605421","https://openalex.org/W3070253958","https://openalex.org/W3080089353","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3105763085","https://openalex.org/W3106779937","https://openalex.org/W3109114891","https://openalex.org/W3111002277","https://openalex.org/W3116298410","https://openalex.org/W3121016465","https://openalex.org/W3141200356","https://openalex.org/W3148677604","https://openalex.org/W3155357996","https://openalex.org/W3175359120","https://openalex.org/W3180770160","https://openalex.org/W3183905093","https://openalex.org/W3186090335","https://openalex.org/W3192148059","https://openalex.org/W3195529437","https://openalex.org/W3201409833","https://openalex.org/W3201519611","https://openalex.org/W3208601549","https://openalex.org/W4213198672","https://openalex.org/W4245551996","https://openalex.org/W4286663339","https://openalex.org/W4288088427","https://openalex.org/W4289665794","https://openalex.org/W4308233968","https://openalex.org/W6787083801"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W2281134365","https://openalex.org/W4310746709","https://openalex.org/W4306309518","https://openalex.org/W4385574037","https://openalex.org/W4386075645"],"abstract_inverted_index":{"In":[0],"this":[1,34,55],"paper,":[2],"we":[3,32,46,162],"explore":[4],"an":[5,14,59,100],"interesting":[6],"question":[7],"of":[8,41,58,169],"what":[9],"can":[10,47,114],"be":[11,24,115],"obtained":[12],"from":[13,177],"8x8":[15,35],"pixel":[16],"video":[17,36,112,157,198],"sequence.":[18],"Surprisingly,":[19],"it":[20],"turns":[21],"out":[22],"to":[23,73,118,146,155],"quite":[25],"a":[26,49,84,108,164],"lot.":[27],"We":[28,53,150,193],"show":[29,160],"that":[30,113,161],"when":[31],"process":[33],"with":[37,93,200],"the":[38,75,172,188,196],"right":[39],"set":[40],"audio":[42,70],"and":[43,79,83,124,128,135,159,190,202],"image":[44,89,123],"priors,":[45],"obtain":[48,163],"full-length,":[50],"256x256":[51],"video.":[52],"achieve":[54],"32x":[56],"scaling":[57],"extremely":[60],"low-resolution":[61],"input":[62],"using":[63],"our":[64,153,178,205],"novel":[65],"audio-visual":[66],"upsampling":[67],"network.":[68],"The":[69,104,175],"prior":[71,90],"helps":[72],"recover":[74],"elemental":[76],"facial":[77],"details":[78],"precise":[80],"lip":[81],"shapes":[82],"single":[85,120],"high-resolution":[86],"target":[87,121],"identity":[88,122],"provides":[91],"us":[92],"rich":[94],"appearance":[95],"details.":[96],"Our":[97,131],"approach":[98,132],"is":[99,133],"end-to-end":[101],"multi-stage":[102],"framework.":[103],"first":[105],"stage":[106],"produces":[107],"coarse":[109],"intermediate":[110],"output":[111],"then":[116],"used":[117],"animate":[119],"generate":[125],"realistic,":[126],"accurate":[127],"high-quality":[129],"outputs.":[130],"simple":[134],"performs":[136],"exceedingly":[137],"well":[138],"(an":[139],"8x":[140],"improvement":[141,166],"in":[142,167],"FID":[143],"score)":[144],"compared":[145],"previous":[147,173],"super-resolution":[148],"methods.":[149],"also":[151,194],"extend":[152],"model":[154],"talking-face":[156],"compression,":[158],"3.5x":[165],"terms":[168],"bits/pixel":[170],"over":[171],"state-of-the-art.":[174],"results":[176],"network":[179],"are":[180],"thoroughly":[181],"analyzed":[182],"through":[183],"extensive":[184],"ablation":[185],"experiments":[186],"(in":[187],"paper":[189],"supplementary":[191],"material).":[192],"provide":[195],"demo":[197],"along":[199],"code":[201],"models":[203],"on":[204],"http://cvit.iiit.ac.in/research/projects/cvit-projects/talking-face-video-upsampling.":[206]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}