{"id":"https://openalex.org/W3028471427","doi":"https://doi.org/10.2352/issn.2470-1173.2020.9.iqsp-167","title":"Analyzing the performance of autoencoder-based objective quality metrics on audio-visual content","display_name":"Analyzing the performance of autoencoder-based objective quality metrics on audio-visual content","publication_year":2020,"publication_date":"2020-01-11","ids":{"openalex":"https://openalex.org/W3028471427","doi":"https://doi.org/10.2352/issn.2470-1173.2020.9.iqsp-167","mag":"3028471427"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2020.9.iqsp-167","is_oa":true,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2020.9.iqsp-167","pdf_url":"https://library.imaging.org/ei/articles/32/9/art00007","source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://library.imaging.org/ei/articles/32/9/art00007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014946755","display_name":"Helard Becerra Martinez","orcid":"https://orcid.org/0000-0003-2652-3195"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Helard Becerra Martinez","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Ireland;"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland;","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022483402","display_name":"Myl\u00e8ne C. Q. Farias","orcid":"https://orcid.org/0000-0002-1957-9943"},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Myl\u00e8ne C.Q. Farias","raw_affiliation_strings":["Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Bras\u00edlia, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I150729083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008608844","display_name":"Andrew Hines","orcid":"https://orcid.org/0000-0001-9636-2556"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Andrew Hines","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Ireland;"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland;","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014946755"],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04439739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"9","first_page":"167","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9897000193595886,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9897000193595886,"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":0.9807999730110168,"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":0.9075000286102295,"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":0.8186649084091187},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8167343139648438},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6639419794082642},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5947820544242859},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5389142632484436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5142009258270264},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5057809352874756},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49279263615608215},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4701155722141266},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4691029489040375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45958012342453003},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45808520913124084},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42893826961517334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3629762530326843},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32419025897979736},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2439689338207245},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1811286211013794},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.07280051708221436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06436717510223389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186649084091187},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8167343139648438},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6639419794082642},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5947820544242859},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5389142632484436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142009258270264},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5057809352874756},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49279263615608215},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4701155722141266},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4691029489040375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45958012342453003},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45808520913124084},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42893826961517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3629762530326843},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32419025897979736},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2439689338207245},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1811286211013794},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.07280051708221436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06436717510223389},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2352/issn.2470-1173.2020.9.iqsp-167","is_oa":true,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2020.9.iqsp-167","pdf_url":"https://library.imaging.org/ei/articles/32/9/art00007","source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},{"id":"pmh:oai:researchrepository.ucd.ie:10197/11353","is_oa":true,"landing_page_url":"http://hdl.handle.net/10197/11353","pdf_url":"http://hdl.handle.net/10197/11353","source":{"id":"https://openalex.org/S4306402280","display_name":"Research Repository UCD (University College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100930933","host_organization_name":"University College Dublin","host_organization_lineage":["https://openalex.org/I100930933"],"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":"Conference Publication"}],"best_oa_location":{"id":"doi:10.2352/issn.2470-1173.2020.9.iqsp-167","is_oa":true,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2020.9.iqsp-167","pdf_url":"https://library.imaging.org/ei/articles/32/9/art00007","source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3028471427.pdf","grobid_xml":"https://content.openalex.org/works/W3028471427.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W305983188","https://openalex.org/W1580389772","https://openalex.org/W1606487971","https://openalex.org/W1728888090","https://openalex.org/W1982471090","https://openalex.org/W2102166818","https://openalex.org/W2131676517","https://openalex.org/W2134561372","https://openalex.org/W2194363988","https://openalex.org/W2623662528","https://openalex.org/W2755560870","https://openalex.org/W2808868772","https://openalex.org/W2977078804","https://openalex.org/W2977844680","https://openalex.org/W2985767095","https://openalex.org/W6637730093"],"related_works":["https://openalex.org/W2384738070","https://openalex.org/W2056404380","https://openalex.org/W2065633372","https://openalex.org/W2328398924","https://openalex.org/W2792033502","https://openalex.org/W2735200146","https://openalex.org/W4225318512","https://openalex.org/W4312624015","https://openalex.org/W1590604789","https://openalex.org/W2084477629"],"abstract_inverted_index":{"The":[0,105,141],"development":[1],"of":[2,9,14,23,34,41,66,69,78,90,144,156],"audio-visual":[3,79,91,163],"quality":[4,29,33,72,139],"models":[5],"faces":[6],"a":[7,35,52,67,75,87],"number":[8],"challenges,":[10],"including":[11],"the":[12,21,32,42,64,150],"integration":[13],"audio":[15,101,127,136],"and":[16,20,102,128,137],"video":[17,103,129,138],"sensory":[18],"channels":[19],"modeling":[22],"their":[24],"interaction":[25],"characteristics.":[26],"Commonly,":[27],"objective":[28,58,71,134],"metrics":[30,73],"estimate":[31],"single":[36],"component":[37],"(audio":[38],"or":[39,152],"video)":[40],"content.":[43,80],"Machine":[44],"learning":[45],"techniques,":[46],"such":[47],"as":[48,51],"autoencoders,":[49],"offer":[50],"very":[53],"promising":[54],"alternative":[55],"to":[56,148],"develop":[57],"assessment":[59],"models.":[60],"This":[61],"paper":[62],"studies":[63],"performance":[65,155],"group":[68],"autoencoder-based":[70,120],"on":[74,112,162],"diverse":[76],"set":[77],"To":[81],"perform":[82],"this":[83,145],"test,":[84],"we":[85],"use":[86],"large":[88],"dataset":[89],"content":[92],"(The":[93],"UnB-AV":[94],"database),":[95],"which":[96,122],"contains":[97],"degradations":[98],"in":[99,154],"both":[100,126],"components.":[104],"database":[106],"has":[107],"accompanying":[108],"subjective":[109,115],"scores":[110],"collected":[111],"three":[113],"separate":[114],"experiments.":[116],"We":[117],"compare":[118],"our":[119],"methods,":[121],"take":[123],"into":[124],"account":[125],"components":[130],"(multi-modal),":[131],"against":[132],"several":[133],"(single-modal)":[135],"metrics.":[140],"main":[142],"goal":[143],"work":[146],"is":[147],"verify":[149],"gain":[151],"loss":[153],"these":[157],"single-modal":[158],"metrics,":[159],"when":[160],"tested":[161],"sequences.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}