{"id":"https://openalex.org/W4224917445","doi":"https://doi.org/10.1109/icassp43922.2022.9747073","title":"Deep Video Inpainting Guided by Audio-Visual Self-Supervision","display_name":"Deep Video Inpainting Guided by Audio-Visual Self-Supervision","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917445","doi":"https://doi.org/10.1109/icassp43922.2022.9747073"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747073","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.07663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083044835","display_name":"Kyuyeon Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuyeon Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing","School of Computing, Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066232134","display_name":"Junsik Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junsik Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing","School of Computing, Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741613","display_name":"Woo Jae Kim","orcid":"https://orcid.org/0000-0002-2826-4177"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo Jae Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing","School of Computing, Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078173428","display_name":"Sung\u2010Eui Yoon","orcid":"https://orcid.org/0000-0002-7123-1119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-Eui Yoon","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST),School of Computing","School of Computing, Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST),School of Computing","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Computing, Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.059,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22751473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"37","issue":null,"first_page":"1970","last_page":"1974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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":0.995199978351593,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9941999912261963,"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/inpainting","display_name":"Inpainting","score":0.8842835426330566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8107600212097168},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6504780650138855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6349167823791504},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5626158714294434},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5025057792663574},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42961585521698},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.42688053846359253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34316954016685486},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2969086468219757},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24826517701148987}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8842835426330566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107600212097168},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6504780650138855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6349167823791504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5626158714294434},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5025057792663574},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42961585521698},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.42688053846359253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34316954016685486},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2969086468219757},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24826517701148987}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747073","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.07663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.07663","pdf_url":"https://arxiv.org/pdf/2310.07663","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.07663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.07663","pdf_url":"https://arxiv.org/pdf/2310.07663","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224917445.pdf","grobid_xml":"https://content.openalex.org/works/W4224917445.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2295107390","https://openalex.org/W2551763541","https://openalex.org/W2619697695","https://openalex.org/W2798365772","https://openalex.org/W2886714066","https://openalex.org/W2914217321","https://openalex.org/W2951611190","https://openalex.org/W2954284167","https://openalex.org/W2962865004","https://openalex.org/W2964109005","https://openalex.org/W2969109746","https://openalex.org/W2970400386","https://openalex.org/W2986330308","https://openalex.org/W2986433113","https://openalex.org/W2988407809","https://openalex.org/W3015669429","https://openalex.org/W3035753399","https://openalex.org/W3095422700","https://openalex.org/W3097348442","https://openalex.org/W3105352633","https://openalex.org/W3123318516","https://openalex.org/W3170088426","https://openalex.org/W4289665794","https://openalex.org/W6747045456","https://openalex.org/W6749633790","https://openalex.org/W6750997056","https://openalex.org/W6765279218","https://openalex.org/W6783539077"],"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/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W4298074124","https://openalex.org/W3214306048","https://openalex.org/W2587407424"],"abstract_inverted_index":{"Humans":[0],"can":[1,130],"easily":[2],"imagine":[3],"a":[4,64,116,132],"scene":[5,148],"from":[6],"auditory":[7,53],"information":[8],"based":[9],"on":[10],"their":[11],"prior":[12,40,69,80],"knowledge":[13,70,81],"of":[14,34,71,105,135],"audio-visual":[15,46,59,72,90,94],"events.":[16],"In":[17],"this":[18,22],"paper,":[19],"we":[20,42],"mimic":[21],"innate":[23],"human":[24],"ability":[25],"in":[26,146],"deep":[27],"learning":[28],"models":[29],"to":[30,74,114,119],"improve":[31,102],"the":[32,39,45,50,58,68,75,103,106,111,143,147],"quality":[33],"video":[35,76,107,136],"inpainting.":[36],"To":[37],"implement":[38],"knowledge,":[41],"first":[43],"train":[44],"network,":[47],"which":[48],"learns":[49],"correspondence":[51,73,118],"between":[52],"and":[54,93,138],"visual":[55],"information.":[56],"Then,":[57],"network":[60],"is":[61,82,139,149],"employed":[62],"as":[63],"guider":[65],"that":[66,126],"conveys":[67],"inpainting":[77,108,112],"network.":[78],"This":[79],"transferred":[83],"through":[84],"our":[85,127],"proposed":[86,128],"two":[87,99],"novel":[88],"losses:":[89],"attention":[91],"loss":[92],"pseudo-class":[95],"consistency":[96],"loss.":[97],"These":[98],"losses":[100],"further":[101],"performance":[104],"by":[109],"encouraging":[110],"result":[113],"have":[115],"high":[117],"its":[120],"synchronized":[121],"audio.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"method":[129],"restore":[131],"wider":[133],"domain":[134],"scenes":[137],"particularly":[140],"effective":[141],"when":[142],"sounding":[144],"object":[145],"partially":[150],"blinded.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}