{"id":"https://openalex.org/W3174174431","doi":"https://doi.org/10.1109/jsac.2022.3221953","title":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","display_name":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","publication_year":2022,"publication_date":"2022-11-16","ids":{"openalex":"https://openalex.org/W3174174431","doi":"https://doi.org/10.1109/jsac.2022.3221953","mag":"3174174431"},"language":"en","primary_location":{"id":"doi:10.1109/jsac.2022.3221953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2022.3221953","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"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 Journal on Selected Areas in Communications","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/A5054094794","display_name":"Pulkit Tandon","orcid":"https://orcid.org/0000-0002-0617-9297"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pulkit Tandon","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086012490","display_name":"Shubham Chandak","orcid":"https://orcid.org/0000-0002-1130-9762"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Chandak","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036506156","display_name":"Pat Pataranutaporn","orcid":"https://orcid.org/0000-0002-1879-7340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pat Pataranutaporn","raw_affiliation_strings":["MIT Media Laboratory, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Media Laboratory, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533871","display_name":"Yimeng Liu","orcid":"https://orcid.org/0000-0002-6742-2908"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yimeng Liu","raw_affiliation_strings":["Department of Computer Science, UC Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019792968","display_name":"Anesu M. Mapuranga","orcid":"https://orcid.org/0000-0003-4445-3354"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anesu M. Mapuranga","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081457786","display_name":"Pattie Maes","orcid":"https://orcid.org/0000-0002-7722-6038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pattie Maes","raw_affiliation_strings":["MIT Media Laboratory, MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Media Laboratory, MIT, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043344688","display_name":"Tsachy Weissman","orcid":"https://orcid.org/0009-0008-1099-691X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsachy Weissman","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029380651","display_name":"Misha Sra","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Misha Sra","raw_affiliation_strings":["Department of Computer Science, UC Santa Barbara, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UC Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5054094794"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.7195,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93819003,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"41","issue":"1","first_page":"107","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9993000030517578,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7851235866546631},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5470959544181824},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5181711912155151},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.4732245206832886},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45297330617904663},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4238613545894623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27954936027526855},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1185615062713623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851235866546631},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5470959544181824},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5181711912155151},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.4732245206832886},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45297330617904663},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4238613545894623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27954936027526855},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1185615062713623},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jsac.2022.3221953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2022.3221953","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"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 Journal on Selected Areas in Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319290","display_name":"Meta","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1496659747","https://openalex.org/W1502560247","https://openalex.org/W2013784666","https://openalex.org/W2047908040","https://openalex.org/W2133249991","https://openalex.org/W2140199336","https://openalex.org/W2154961933","https://openalex.org/W2155292833","https://openalex.org/W2162598851","https://openalex.org/W2168346408","https://openalex.org/W2170931744","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2793476612","https://openalex.org/W2804619907","https://openalex.org/W2891639355","https://openalex.org/W2914217321","https://openalex.org/W2960274051","https://openalex.org/W2962713165","https://openalex.org/W2963143316","https://openalex.org/W2963841322","https://openalex.org/W2969174745","https://openalex.org/W2970315999","https://openalex.org/W2971775690","https://openalex.org/W2981263323","https://openalex.org/W2981767644","https://openalex.org/W2987809065","https://openalex.org/W2994760783","https://openalex.org/W3006538026","https://openalex.org/W3007419529","https://openalex.org/W3008823916","https://openalex.org/W3015735225","https://openalex.org/W3015812362","https://openalex.org/W3019952993","https://openalex.org/W3025051722","https://openalex.org/W3033915435","https://openalex.org/W3034368386","https://openalex.org/W3034371424","https://openalex.org/W3036601975","https://openalex.org/W3036851434","https://openalex.org/W3080642835","https://openalex.org/W3081492798","https://openalex.org/W3089089004","https://openalex.org/W3095664976","https://openalex.org/W3097792222","https://openalex.org/W3099782249","https://openalex.org/W3101631197","https://openalex.org/W3104152799","https://openalex.org/W3105763085","https://openalex.org/W3109114891","https://openalex.org/W3112819734","https://openalex.org/W3113050802","https://openalex.org/W3127279334","https://openalex.org/W3129576130","https://openalex.org/W3138154797","https://openalex.org/W3158108395","https://openalex.org/W3163045957","https://openalex.org/W3166791908","https://openalex.org/W3176721746","https://openalex.org/W3177150198","https://openalex.org/W3180770160","https://openalex.org/W3186090001","https://openalex.org/W3186700381","https://openalex.org/W3195529437","https://openalex.org/W4200295417","https://openalex.org/W4226150551","https://openalex.org/W4287327028","https://openalex.org/W4294541506","https://openalex.org/W4295289379","https://openalex.org/W6630236247","https://openalex.org/W6683074461","https://openalex.org/W6753914649","https://openalex.org/W6763239785","https://openalex.org/W6767264202","https://openalex.org/W6780218876","https://openalex.org/W6790978476","https://openalex.org/W6794682062","https://openalex.org/W6810966997","https://openalex.org/W6840899668"],"related_works":["https://openalex.org/W3208761720","https://openalex.org/W2592064417","https://openalex.org/W2353272253","https://openalex.org/W2245085077","https://openalex.org/W1555023417","https://openalex.org/W3178731955","https://openalex.org/W2890911786","https://openalex.org/W2126491259","https://openalex.org/W2100712766","https://openalex.org/W1560709196"],"abstract_inverted_index":{"Video":[0],"represents":[1],"the":[2,13,25,32,40,124,152,157,190],"majority":[3],"of":[4,15,20,27,42,123,148],"internet":[5,203],"traffic":[6],"today,":[7],"driving":[8],"a":[9,37,62,70,90,110,120,168],"continual":[10],"race":[11],"between":[12],"generation":[14],"higher":[16],"quality":[17],"content,":[18,80],"transmission":[19,101],"larger":[21],"file":[22],"sizes,":[23],"and":[24,78,117,136],"development":[26],"network":[28,74],"infrastructure.":[29],"In":[30],"addition,":[31],"recent":[33,128],"COVID-19":[34],"pandemic":[35],"fueled":[36],"surge":[38],"in":[39,130,151,181,206],"use":[41],"video":[43,66,92,126],"conferencing":[44],"tools.":[45],"Since":[46],"videos":[47,106],"take":[48],"up":[49,189],"considerable":[50],"bandwidth":[51],"(":[52,173],"<inline-formula":[53,174],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54,175,221],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[55,176],"<tex-math":[56,177],"notation=\"LaTeX\">$\\sim":[57],"100$":[58],"</tex-math></inline-formula>":[59,179],"Kbps":[60],"to":[61,84,109,145,156],"few":[63],"Mbps),":[64],"improved":[65],"compression":[67,93],"can":[68],"have":[69],"substantial":[71],"impact":[72],"on":[73,167],"performance":[75],"for":[76,192,214],"live":[77],"pre-recorded":[79],"providing":[81],"broader":[82],"access":[83],"multimedia":[85],"content":[86],"worldwide.":[87],"We":[88],"present":[89],"novel":[91,194],"pipeline,":[94],"called":[95],"Txt2Vid,":[96],"which":[97],"dramatically":[98],"reduces":[99],"data":[100],"rates":[102],"by":[103,171],"compressing":[104],"webcam":[105],"(\u201ctalking-head":[107],"videos\u201d)":[108],"text":[111,114],"transcript.":[112],"The":[113,185,212],"is":[115,217],"transmitted":[116],"decoded":[118],"into":[119],"realistic":[121],"reconstruction":[122],"original":[125],"using":[127],"advances":[129],"deep":[131],"learning":[132],"based":[133,166],"voice":[134],"cloning":[135],"lip":[137],"syncing":[138],"models.":[139],"Our":[140],"generative":[141],"pipeline":[142],"achieves":[143],"two":[144],"three":[146],"orders":[147],"magnitude":[149],"reduction":[150],"bitrate":[153],"as":[154,197],"compared":[155],"standard":[158],"audio-video":[159,199],"codecs":[160],"(encoders-decoders),":[161],"while":[162],"maintaining":[163],"equivalent":[164],"Quality-of-Experience":[165],"subjective":[169],"evaluation":[170],"users":[172],"notation=\"LaTeX\">$n=242$":[178],")":[180],"an":[182],"online":[183],"study.":[184],"Txt2Vid":[186],"framework":[187],"opens":[188],"potential":[191],"creating":[193],"applications":[195],"such":[196],"enabling":[198],"communication":[200],"during":[201],"poor":[202],"connectivity,":[204],"or":[205],"remote":[207],"terrains":[208],"with":[209],"limited":[210],"bandwidth.":[211],"code":[213],"this":[215],"work":[216],"available":[218],"at":[219],"<uri":[220],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/tpulkit/txt2vid.git</uri>":[222],".":[223]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}