{"id":"https://openalex.org/W3013502202","doi":"https://doi.org/10.1109/qomex48832.2020.9123142","title":"How Deep is Your Encoder: An Analysis of Features Descriptors for an Autoencoder-Based Audio-Visual Quality Metric","display_name":"How Deep is Your Encoder: An Analysis of Features Descriptors for an Autoencoder-Based Audio-Visual Quality Metric","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3013502202","doi":"https://doi.org/10.1109/qomex48832.2020.9123142","mag":"3013502202"},"language":"en","primary_location":{"id":"doi:10.1109/qomex48832.2020.9123142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qomex48832.2020.9123142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.11100","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 Martinez","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Ireland","Univ. College Dublin"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]},{"raw_affiliation_string":"Univ. College Dublin","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","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","Univ. College Dublin"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]},{"raw_affiliation_string":"Univ. College Dublin","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","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":"Mylene C. Q. Farias","raw_affiliation_strings":["University of Bras\u00edlia, Brasilia, Brazil","Department of Electrical Engineering, University of Brasilia \u2013 UnB, Bras\u00edlia, Brazil"],"affiliations":[{"raw_affiliation_string":"University of Bras\u00edlia, Brasilia, Brazil","institution_ids":["https://openalex.org/I150729083"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Brasilia \u2013 UnB, Bras\u00edlia, Brazil","institution_ids":["https://openalex.org/I150729083"]}]}],"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":0.0981,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3719396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9947999715805054,"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/T11666","display_name":"Color Science and Applications","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.8733972311019897},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8729726076126099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749580144882202},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6886958479881287},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6565214991569519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5968758463859558},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5816760063171387},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5622227191925049},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5527597069740295},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4946853816509247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41747021675109863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3941797912120819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3763345777988434},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2832068204879761},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13549759984016418},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.066103994846344}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.8733972311019897},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8729726076126099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749580144882202},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6886958479881287},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6565214991569519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968758463859558},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5816760063171387},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5622227191925049},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5527597069740295},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4946853816509247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41747021675109863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3941797912120819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3763345777988434},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2832068204879761},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13549759984016418},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.066103994846344},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/qomex48832.2020.9123142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qomex48832.2020.9123142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.11100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.11100","pdf_url":"https://arxiv.org/pdf/2003.11100","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:researchrepository.ucd.ie:10197/12211","is_oa":true,"landing_page_url":"http://hdl.handle.net/10197/12211","pdf_url":"http://hdl.handle.net/10197/12211","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"},{"id":"mag:3013502202","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2003.11100.pdf","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.11100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.11100","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.11100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.11100","pdf_url":"https://arxiv.org/pdf/2003.11100","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1488196772","display_name":null,"funder_award_id":"2/RC/2289_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2545334760","display_name":null,"funder_award_id":"12/RC/2289 P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3005632379","display_name":null,"funder_award_id":"3/RC/2077","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3331681876","display_name":null,"funder_award_id":"CAPES","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3695527833","display_name":null,"funder_award_id":"12/RC/2289_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3938906640","display_name":null,"funder_award_id":"(CAPES)","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G4206737522","display_name":null,"funder_award_id":"13/RC/207","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4699366015","display_name":null,"funder_award_id":"FAPDF","funder_id":"https://openalex.org/F4320310929","funder_display_name":"Universidade de Bras\u00edlia"},{"id":"https://openalex.org/G5098725405","display_name":null,"funder_award_id":"12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G5129370892","display_name":null,"funder_award_id":"CAPES","funder_id":"https://openalex.org/F4320310929","funder_display_name":"Universidade de Bras\u00edlia"},{"id":"https://openalex.org/G5318036630","display_name":null,"funder_award_id":"3/RC/2077","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G6586979110","display_name":null,"funder_award_id":"13/RC/2077","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6607374863","display_name":null,"funder_award_id":"12/RC/2289_P2","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6712843611","display_name":null,"funder_award_id":"12/RC/228","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7226090481","display_name":null,"funder_award_id":"13/RC/2077","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7362007176","display_name":null,"funder_award_id":"12/RC/2289","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320310929","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59"},{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323350","display_name":"Funda\u00e7\u00e3o de Apoio \u00e0 Pesquisa do Distrito Federal","ror":"https://ror.org/04djvx395"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W171309019","https://openalex.org/W1965754316","https://openalex.org/W1982471090","https://openalex.org/W2025769979","https://openalex.org/W2048060925","https://openalex.org/W2105854852","https://openalex.org/W2128803215","https://openalex.org/W2131676517","https://openalex.org/W2132549992","https://openalex.org/W2194363988","https://openalex.org/W2547456631","https://openalex.org/W2561217444","https://openalex.org/W2623662528","https://openalex.org/W2755560870","https://openalex.org/W2785586734","https://openalex.org/W2913860539","https://openalex.org/W2969223534","https://openalex.org/W2971151126","https://openalex.org/W2977844680","https://openalex.org/W2985767095","https://openalex.org/W3011052825","https://openalex.org/W6728977757","https://openalex.org/W6731171211","https://openalex.org/W6758949196"],"related_works":["https://openalex.org/W3037192005","https://openalex.org/W2985767095","https://openalex.org/W2952902089","https://openalex.org/W3148634217","https://openalex.org/W2025954386","https://openalex.org/W2785892019","https://openalex.org/W3095909497","https://openalex.org/W34233450","https://openalex.org/W2483684792","https://openalex.org/W3198586259","https://openalex.org/W2939663618","https://openalex.org/W2996158613","https://openalex.org/W2908965201","https://openalex.org/W2968808972","https://openalex.org/W2775447703","https://openalex.org/W3034742263","https://openalex.org/W2770520232","https://openalex.org/W2101305062","https://openalex.org/W3129231202","https://openalex.org/W2158461964"],"abstract_inverted_index":{"The":[0,44,64,107,139],"development":[1],"of":[2,10,19,25,69,80,91,103,118,135,156],"audio-visual":[3,86,105,166],"quality":[4,167],"assessment":[5],"models":[6],"poses":[7],"a":[8,51,60,77,101,132,163],"number":[9],"challenges":[11,21],"in":[12,142],"order":[13],"to":[14,83,95,130,151],"obtain":[15],"accurate":[16,97],"predictions.":[17],"One":[18],"these":[20],"is":[22,39],"the":[23,26,85,115,119,136,153,157],"modelling":[24],"complex":[27],"interaction":[28,38],"that":[29,148],"audio":[30,70],"and":[31,35,71,75,160],"visual":[32],"stimuli":[33],"have":[34,131],"how":[36],"this":[37,57,143],"interpreted":[40],"by":[41],"human":[42],"users.":[43],"No-Reference":[45],"Audio-Visual":[46],"Quality":[47],"Metric":[48],"Based":[49],"on":[50,114],"Deep":[52],"Autoencoder":[53],"(NAViDAd)":[54],"deals":[55],"with":[56,100],"problem":[58],"from":[59],"machine":[61],"learning":[62],"perspective.":[63],"metric":[65,137],"receives":[66],"two":[67],"sets":[68],"video":[72],"features":[73,81],"descriptors":[74],"produces":[76],"low-dimensional":[78],"set":[79],"used":[82],"predict":[84],"quality.":[87],"A":[88],"basic":[89],"implementation":[90],"NAViDAd":[92],"was":[93],"able":[94],"produce":[96],"predictions":[98],"tested":[99],"range":[102],"different":[104,128],"databases.":[106],"current":[108],"work":[109],"performs":[110],"an":[111],"ablation":[112],"study":[113,144],"base":[116],"architecture":[117,159],"metric.":[120,168],"Several":[121],"modules":[122],"are":[123],"removed":[124],"or":[125],"re-trained":[126],"using":[127],"configurations":[129],"better":[133,165],"understanding":[134],"functionality.":[138],"results":[140],"presented":[141],"provided":[145],"important":[146],"feedback":[147],"allows":[149],"us":[150],"understand":[152],"real":[154],"capacity":[155],"metric's":[158],"eventually":[161],"develop":[162],"much":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}