{"id":"https://openalex.org/W4375868873","doi":"https://doi.org/10.1109/icassp49357.2023.10095711","title":"LSTM-Based Video Quality Prediction Accounting for Temporal Distortions in Videoconferencing Calls","display_name":"LSTM-Based Video Quality Prediction Accounting for Temporal Distortions in Videoconferencing Calls","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868873","doi":"https://doi.org/10.1109/icassp49357.2023.10095711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069979525","display_name":"Gabriel Mittag","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Gabriel Mittag","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069905492","display_name":"Babak Naderi","orcid":"https://orcid.org/0009-0006-4778-5417"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Babak Naderi","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067566","display_name":"Vishak Gopal","orcid":"https://orcid.org/0009-0005-3887-1439"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Vishak Gopal","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210105678"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":1.0,"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":1.0,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9951000213623047,"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/T11019","display_name":"Image Enhancement Techniques","score":0.984499990940094,"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":0.872057318687439},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.7791037559509277},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.7294860482215881},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6132806539535522},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.574410617351532},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5282247066497803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4526101350784302},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45016512274742126},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.29829293489456177},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11287489533424377},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09717312455177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.872057318687439},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.7791037559509277},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.7294860482215881},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6132806539535522},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.574410617351532},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5282247066497803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4526101350784302},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45016512274742126},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29829293489456177},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11287489533424377},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09717312455177307},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":21,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2044338482","https://openalex.org/W2076136231","https://openalex.org/W2114173475","https://openalex.org/W2117804578","https://openalex.org/W2127877311","https://openalex.org/W2133665775","https://openalex.org/W2165222134","https://openalex.org/W2736492128","https://openalex.org/W2793889002","https://openalex.org/W2810598854","https://openalex.org/W2888880110","https://openalex.org/W2965644659","https://openalex.org/W3015337948","https://openalex.org/W3093720944","https://openalex.org/W3099047215","https://openalex.org/W3174089122","https://openalex.org/W4295096708","https://openalex.org/W4295677767","https://openalex.org/W6734148010","https://openalex.org/W6842070654"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"video":[2,16,132],"quality":[3,57,123,133],"models,":[4],"such":[5,48],"as":[6,79],"VMAF,":[7],"give":[8],"excellent":[9],"prediction":[10],"results":[11],"by":[12,51],"comparing":[13],"the":[14,82,95,115,129],"degraded":[15],"with":[17,55,102],"its":[18],"reference":[19],"video.":[20],"However,":[21],"they":[22],"do":[23],"not":[24],"consider":[25],"temporal":[26,91],"distortions":[27,49],"(e.g.,":[28],"frame":[29],"freezes":[30],"or":[31],"skips)":[32],"that":[33,124],"occur":[34],"during":[35],"videoconferencing":[36,68],"calls.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"a":[43,110],"data-driven":[44],"approach":[45],"for":[46],"modeling":[47],"automatically":[50],"training":[52],"an":[53],"LSTM":[54],"subjective":[56],"ratings":[58],"labeled":[59],"via":[60],"crowdsourcing.":[61],"The":[62,135],"videos":[63,84],"were":[64],"collected":[65],"from":[66],"live":[67],"calls":[69],"in":[70],"83":[71],"different":[72],"network":[73],"conditions.":[74],"We":[75],"applied":[76],"QR":[77],"codes":[78],"markers":[80],"on":[81,94,114],"source":[83],"to":[85],"create":[86],"aligned":[87],"references":[88],"and":[89,138],"compute":[90],"features":[92,100],"based":[93],"alignment":[96],"vectors.":[97],"Using":[98],"these":[99],"together":[101],"VMAF":[103],"core":[104],"features,":[105],"our":[106,119],"proposed":[107],"model":[108,120,137],"achieves":[109],"PCC":[111],"of":[112,131],"0.99":[113],"validation":[116],"set.":[117],"Furthermore,":[118],"outputs":[121],"per-frame":[122],"gives":[125],"detailed":[126],"insight":[127],"into":[128],"cause":[130],"impairments.":[134],"VCM":[136],"dataset":[139],"are":[140],"open-sourced":[141],"at":[142],"https://github.com/microsoft/Video_Call_MOS.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
