{"id":"https://openalex.org/W7009899463","doi":null,"title":"Generative Adversarial Networks in Lip-Synchronized Deepfakes for Personalized Video Messages","display_name":"Generative Adversarial Networks in Lip-Synchronized Deepfakes for Personalized Video Messages","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W7009899463"},"language":"en","primary_location":{"id":"pmh:oai:lup-student-papers.lub.lu.se:9060411","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9060411","pdf_url":"http://lup.lub.lu.se/student-papers/record/9060411","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"H2"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://lup.lub.lu.se/student-papers/record/9060411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011649626","display_name":"Johan Liljegren","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liljegren, Johan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075848540","display_name":"Pontus Nordqvist","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nordqvist, Pontus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.986299991607666,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.986299991607666,"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":0.005900000222027302,"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/T10860","display_name":"Speech and Audio Processing","score":0.004000000189989805,"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/deepfakes","display_name":"deepfakes","score":0.9089999794960022},{"id":"https://openalex.org/keywords/lip-synchronization","display_name":"lip synchronization","score":0.968999981880188},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.9520000219345093},{"id":"https://openalex.org/keywords/wgan-gp","display_name":"WGAN-GP","score":0.953000009059906},{"id":"https://openalex.org/keywords/grid-dataset","display_name":"GRID dataset","score":0.7089999914169312},{"id":"https://openalex.org/keywords/mode-collapse","display_name":"mode collapse","score":0.7870000004768372},{"id":"https://openalex.org/keywords/training-set-size","display_name":"training data size","score":0.5979999899864197},{"id":"https://openalex.org/keywords/video-to-video-translation","display_name":"video-to-video translation","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252999782562256},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656499981880188},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5759000182151794},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.3449999988079071},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33059999346733093},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:lup-student-papers.lub.lu.se:9060411","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9060411","pdf_url":"http://lup.lub.lu.se/student-papers/record/9060411","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"H2"}],"best_oa_location":{"id":"pmh:oai:lup-student-papers.lub.lu.se:9060411","doi":null,"is_oa":true,"landing_page_url":"http://lup.lub.lu.se/student-papers/record/9060411","pdf_url":"http://lup.lub.lu.se/student-papers/record/9060411","source":{"id":"https://openalex.org/S4306402420","display_name":"Lund University Publications Student Papers (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"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":"H2"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7009899463.pdf","grobid_xml":"https://content.openalex.org/works/W7009899463.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W1813599753","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2173520492","https://openalex.org/W2432004435","https://openalex.org/W2581485081","https://openalex.org/W2593414223","https://openalex.org/W2605135824","https://openalex.org/W2759973161","https://openalex.org/W2766527293","https://openalex.org/W2768599997","https://openalex.org/W2775288145","https://openalex.org/W2782422271","https://openalex.org/W2786010873","https://openalex.org/W2786015036","https://openalex.org/W2792263949","https://openalex.org/W2802061317","https://openalex.org/W2890952074","https://openalex.org/W2931364255","https://openalex.org/W2945216816","https://openalex.org/W2949650786","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963981733","https://openalex.org/W2964121744","https://openalex.org/W2978419469","https://openalex.org/W2980104607","https://openalex.org/W2981767644","https://openalex.org/W2985516053","https://openalex.org/W3013117577","https://openalex.org/W3030163527","https://openalex.org/W3035965352","https://openalex.org/W3037567775","https://openalex.org/W3134644013","https://openalex.org/W3192148059","https://openalex.org/W4298289240","https://openalex.org/W4394665544"],"related_works":["https://openalex.org/W4313303633","https://openalex.org/W4390871677","https://openalex.org/W4415796454","https://openalex.org/W4417233416","https://openalex.org/W7165663984","https://openalex.org/W3038385261","https://openalex.org/W7122677257","https://openalex.org/W4402980407","https://openalex.org/W4285268113","https://openalex.org/W4402422516"],"abstract_inverted_index":{"The":[0,81],"recent":[1],"progress":[2],"of":[3,49,94,169,179,214,263],"deep":[4,64],"learning":[5,65],"has":[6],"enabled":[7],"more":[8],"powerful":[9],"frameworks":[10],"to":[11,26,53,72,84,88,129,225,249,293],"create":[12],"good-quality":[13],"deepfakes.":[14,59],"Deepfakes,":[15],"which":[16,45],"are":[17],"mostly":[18],"known":[19],"for":[20],"malicious":[21],"purposes,":[22],"have":[23],"great":[24],"potential":[25],"be":[27],"useful":[28],"in":[29,120,195,212],"areas":[30],"such":[31],"as":[32],"the":[33,63,106,114,130,154,160,167,170,200,207,226,241,250,257,273,283],"movie":[34],"industry,":[35],"education,":[36],"and":[37,76,100,133,147,157,164,193,216,287],"personalized":[38,55],"messaging.":[39],"This":[40],"thesis":[41],"focus":[42],"on":[43,185,240,254,260,272],"lip-synchronization,":[44,90],"is":[46],"a":[47,50,73,86,123,135],"part":[48],"broader":[51],"pipeline":[52],"develop":[54],"video":[56,77],"messages,":[57],"using":[58,153],"For":[60,199],"this":[61,98],"application,":[62],"framework":[66],"Generative":[67],"Adversarial":[68],"Networks":[69],"(GAN),":[70],"adapted":[71,128],"given":[74],"audio":[75],"input,":[78],"was":[79,118,127,145,173,282],"used.":[80],"objectives":[82],"were":[83,111,151,233,265,270],"implement":[85],"structure":[87],"perform":[89],"investigate":[91],"what":[92],"variations":[93],"GANs":[95],"excel":[96],"at":[97],"task,":[99],"also":[101],"how":[102],"different":[103,109],"datasets":[104],"impact":[105],"results.":[107],"Three":[108],"models":[110,150,238,258,268],"investigated:":[112],"firstly,":[113],"GAN":[115,124],"architecture":[116],"LipGAN":[117,131,180,208,223,281],"reimplemented":[119],"Pytorch,":[121],"secondly,":[122],"variation,":[125],"WGAN-GP,":[126],"architecture,":[132],"thirdly,":[134],"novel":[136],"approach":[137],"that":[138,206,232,269,280],"takes":[139],"inspiration":[140],"from":[141],"both":[142],"models,":[143,203],"L1WGAN-GP,":[144],"developed":[146],"implemented.":[148],"All":[149],"trained":[152,184,239,253,259,271],"dataset":[155,172,243],"GRID":[156,242],"benchmarked":[158],"by":[159,175,235,267],"metrics":[161],"PSNR,":[162],"SSIM,":[163,217],"FID-score.":[165,227],"Lastly,":[166],"influence":[168],"training":[171],"tested":[174],"comparing":[176],"our":[177,277],"implementation":[178,183,209],"with":[181,288],"another":[182,186],"dataset,":[187],"LRS2.":[188,255],"WGAN-GP":[189],"did":[190],"not":[191],"converge":[192],"resulted":[194],"suspected":[196],"mode":[197],"collapse.":[198],"two":[201],"other":[202],"we":[204,290],"showed":[205,244],"performed":[210,220],"best":[211,284],"terms":[213],"PSNR":[215],"whereas":[218],"L1WGAN-GP":[219,229],"better":[221],"than":[222],"according":[224],"Yet,":[228],"produced":[230],"samples":[231],"polluted":[234],"artifacts.":[236],"Our":[237],"bad":[245],"generalization":[246],"performance":[247],"compared":[248],"same":[251],"model":[252],"Additionally,":[256],"less":[261],"amount":[262],"data":[264],"outperformed":[266],"full":[274],"dataset.":[275],"Finally,":[276],"results":[278],"suggest":[279],"performing":[285],"network,":[286],"it":[289],"successfully":[291],"managed":[292],"produce":[294],"satisfying":[295],"lip-synchronization.":[296]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}