{"id":"https://openalex.org/W4402981633","doi":"https://doi.org/10.1109/icme57554.2024.10687669","title":"NeRVA: Joint Implicit Neural Representations for Videos and Audios","display_name":"NeRVA: Joint Implicit Neural Representations for Videos and Audios","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981633","doi":"https://doi.org/10.1109/icme57554.2024.10687669"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5075660915","display_name":"Anustup Choudhury","orcid":"https://orcid.org/0000-0001-6618-9211"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anustup Choudhury","raw_affiliation_strings":["Dolby Laboratories Inc.,Sunnyvale,CA,USA"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories Inc.,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110536106","display_name":"Praneet Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praneet Singh","raw_affiliation_strings":["Purdue University,West Lafayette,IN,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012578054","display_name":"Guan\u2010Ming Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guan-Ming Su","raw_affiliation_strings":["Dolby Laboratories Inc.,Sunnyvale,CA,USA"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories Inc.,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I4210093996"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075660915"],"corresponding_institution_ids":["https://openalex.org/I4210093996"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70489346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.982699990272522,"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/T11309","display_name":"Music and Audio Processing","score":0.982699990272522,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9735999703407288,"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":0.9491999745368958,"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/joint","display_name":"Joint (building)","score":0.6394469738006592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5691184997558594},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42556023597717285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3796595633029938},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09836268424987793},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05870649218559265}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6394469738006592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5691184997558594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42556023597717285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3796595633029938},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09836268424987793},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05870649218559265}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2613677041","https://openalex.org/W2964109005","https://openalex.org/W2972478942","https://openalex.org/W3031546776","https://openalex.org/W3211147706","https://openalex.org/W4297846303","https://openalex.org/W4312493191","https://openalex.org/W4321504965","https://openalex.org/W4386065502","https://openalex.org/W4386071704","https://openalex.org/W4386811887","https://openalex.org/W4390872116","https://openalex.org/W4393372962","https://openalex.org/W6606244218","https://openalex.org/W6779753539","https://openalex.org/W6780179280","https://openalex.org/W6803392726","https://openalex.org/W6803493554","https://openalex.org/W6810700606","https://openalex.org/W6811329210","https://openalex.org/W6846436217","https://openalex.org/W6848494600","https://openalex.org/W6849227153"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Neural":[0],"fields":[1],"also":[2,65,122],"known":[3],"as":[4,86,93],"implicit":[5],"neural":[6,50,62,69,81,88,108],"representations":[7],"(INR)":[8],"have":[9],"recently":[10],"been":[11],"shown":[12],"to":[13],"be":[14],"quite":[15],"effective":[16],"at":[17],"representing":[18,53,73,136],"video":[19,22,36,147],"content.":[20],"However,":[21],"content":[23,130],"typically":[24],"contains":[25],"audio":[26,42,54,59,104],"and":[27,37,76,95,102,118,148],"existing":[28],"works":[29],"on":[30],"INR":[31,40],"do":[32],"not":[33,44],"represent":[34,58,84],"both":[35,74],"audio.":[38],"Since":[39],"for":[41,52,71,146,151],"is":[43],"well-explored,":[45],"we":[46],"propose":[47,66],"a":[48,61,67,80,87,112],"novel":[49,68],"representation":[51,70,127],"(NeRA)":[55],"that":[56,90,124],"can":[57],"using":[60,79],"network.":[63,82],"We":[64,83,121],"jointly":[72],"videos":[75],"audios":[77],"(NeRVA)":[78],"multimedia":[85,129,140],"network":[89,109],"takes":[91],"timestamp":[92],"input":[94],"outputs":[96],"the":[97,103,137],"corresponding":[98],"RGB":[99],"image":[100],"frame":[101],"samples.":[105],"The":[106],"proposed":[107],"architecture":[110],"uses":[111],"combination":[113],"of":[114,128,139,143],"Multi-Layer":[115],"Perceptron":[116],"(MLP)":[117],"convolutional":[119],"blocks.":[120],"demonstrate":[123],"our":[125],"joint":[126],"has":[131],"better":[132],"performance":[133],"than":[134],"individually":[135],"components":[138],"(An":[141],"improvement":[142],"+2dB":[144],"PSNR":[145],"10\u00d7":[149],"FAD":[150],"audio).":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
