{"id":"https://openalex.org/W3015669429","doi":"https://doi.org/10.1109/icassp40776.2020.9053184","title":"Audio-Assisted Image Inpainting for Talking Faces","display_name":"Audio-Assisted Image Inpainting for Talking Faces","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015669429","doi":"https://doi.org/10.1109/icassp40776.2020.9053184","mag":"3015669429"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5055069331","display_name":"Alexandros Koumparoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Alexandros Koumparoulis","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Thessaly, Volos, Greece"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Thessaly, Volos, Greece"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edmilson da Silva Morais","raw_affiliation_strings":["IBM Research AI, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055069331"],"corresponding_institution_ids":["https://openalex.org/I145722265"],"apc_list":null,"apc_paid":null,"fwci":0.4907,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65000166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"36","issue":null,"first_page":"7664","last_page":"7668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9983000159263611,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.8453725576400757},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.7867953181266785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6691296100616455},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6423921585083008},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5882889032363892},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5468520522117615},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5090103149414062},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45551222562789917},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44224926829338074},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4378882944583893},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4358171224594116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37900280952453613},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19541457295417786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453725576400757},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.7867953181266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6691296100616455},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6423921585083008},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5882889032363892},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5468520522117615},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5090103149414062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45551222562789917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44224926829338074},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4378882944583893},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4358171224594116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37900280952453613},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19541457295417786},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/75306","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/75306","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2029199293","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2331128040","https://openalex.org/W2557414982","https://openalex.org/W2738406145","https://openalex.org/W2739748921","https://openalex.org/W2766290211","https://openalex.org/W2785678896","https://openalex.org/W2798365772","https://openalex.org/W2883861033","https://openalex.org/W2884460600","https://openalex.org/W2914859359","https://openalex.org/W2959650063","https://openalex.org/W2962767869","https://openalex.org/W2963009026","https://openalex.org/W2963081548","https://openalex.org/W2963255313","https://openalex.org/W2963420272","https://openalex.org/W2963836885","https://openalex.org/W2963887671","https://openalex.org/W2963917315","https://openalex.org/W2964350391","https://openalex.org/W2982763192","https://openalex.org/W2990452356","https://openalex.org/W3043547428","https://openalex.org/W6639824700","https://openalex.org/W6694260854","https://openalex.org/W6702130928","https://openalex.org/W6704369950","https://openalex.org/W6730152530","https://openalex.org/W6737896281","https://openalex.org/W6741832134","https://openalex.org/W6745153919","https://openalex.org/W6748582592","https://openalex.org/W6753894364","https://openalex.org/W6765657114"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W4226517663","https://openalex.org/W4308234225","https://openalex.org/W2162778274","https://openalex.org/W2999351684","https://openalex.org/W4200625923"],"abstract_inverted_index":{"The":[0,93],"goal":[1],"of":[2,10,12],"our":[3],"work":[4],"is":[5,96],"to":[6,85,98],"complete":[7],"missing":[8],"areas":[9],"images":[11],"talking":[13,110],"faces,":[14,111],"exploiting":[15],"information":[16,38],"from":[17,109],"both":[18,64],"the":[19,40],"visual":[20,31,65],"and":[21,66,106,115],"audio":[22,67],"modalities.":[23],"Existing":[24],"image":[25],"inpainting":[26],"methods":[27],"rely":[28],"solely":[29],"on":[30],"content":[32],"that":[33,50],"doesn't":[34],"always":[35],"provide":[36],"sufficient":[37],"for":[39,82],"task.":[41],"To":[42],"counter":[43],"this,":[44],"we":[45],"propose":[46],"a":[47,56,77],"neural":[48],"network":[49],"employs":[51],"an":[52],"encoder-decoder":[53],"architecture":[54],"with":[55],"bimodal":[57],"fusion":[58],"mechanism,":[59],"thus":[60],"taking":[61],"into":[62],"account":[63],"content.":[68],"Our":[69],"proposed":[70],"method":[71],"demonstrates":[72],"consistently":[73],"superior":[74],"performance":[75],"over":[76],"baseline":[78],"visual-only":[79],"model,":[80],"reaching":[81],"example":[83],"up":[84],"17%":[86],"relative":[87],"improvement":[88],"in":[89],"mean":[90],"absolute":[91],"error.":[92],"presented":[94],"model":[95],"applicable":[97,121],"practical":[99],"video":[100],"editing":[101],"tasks,":[102],"such":[103],"as":[104,122],"object":[105],"overlay-text":[107],"removal":[108],"where":[112],"existing":[113],"lip":[114],"face":[116],"generation":[117],"works":[118],"are":[119],"not":[120],"they":[123],"require":[124],"clean":[125],"input.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}