{"id":"https://openalex.org/W4415708385","doi":"https://doi.org/10.1109/icme59968.2025.11209273","title":"Research on Audio-Visual Quality Assessment Dataset and Method for User-Generated Omnidirectional Video","display_name":"Research on Audio-Visual Quality Assessment Dataset and Method for User-Generated Omnidirectional Video","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708385","doi":"https://doi.org/10.1109/icme59968.2025.11209273"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102019396","display_name":"Fei Zhao","orcid":"https://orcid.org/0009-0003-8535-4923"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Zhao","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069799853","display_name":"Da Pan","orcid":"https://orcid.org/0000-0001-5402-2713"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Pan","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068085906","display_name":"Zelu Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zelu Qi","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046998734","display_name":"Ping Shi","orcid":"https://orcid.org/0000-0001-7955-5567"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Shi","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.45260000228881836,"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/T10860","display_name":"Speech and Audio Processing","score":0.45260000228881836,"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/T11439","display_name":"Video Analysis and Summarization","score":0.28349998593330383,"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/T11309","display_name":"Music and Audio Processing","score":0.07599999755620956,"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/omnidirectional-antenna","display_name":"Omnidirectional antenna","score":0.769599974155426},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6870999932289124},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6456000208854675},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5899999737739563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5519999861717224},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4717000126838684}],"concepts":[{"id":"https://openalex.org/C24027999","wikidata":"https://www.wikidata.org/wiki/Q2176348","display_name":"Omnidirectional antenna","level":3,"score":0.769599974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7193999886512756},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6870999932289124},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5899999737739563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4848000109195709},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.44679999351501465},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W633914053","https://openalex.org/W2999222884","https://openalex.org/W3091452821","https://openalex.org/W3166201206","https://openalex.org/W3212279368","https://openalex.org/W4224236877","https://openalex.org/W4289387930","https://openalex.org/W4312818079","https://openalex.org/W4313405549","https://openalex.org/W4380480665","https://openalex.org/W4386066074","https://openalex.org/W4387250105","https://openalex.org/W4387969495","https://openalex.org/W4390533518","https://openalex.org/W4390874113","https://openalex.org/W4391488862","https://openalex.org/W4392939676"],"related_works":[],"abstract_inverted_index":{"In":[0],"response":[1],"to":[2,22,84,97],"the":[3,7,27,82,86,92,99,113,118,145],"rising":[4],"prominence":[5],"of":[6,29,45,64,91,101,116,122],"Meta-Verse,":[8],"omnidirectional":[9,47,65],"videos":[10,54,69],"(ODVs)":[11],"have":[12],"garnered":[13],"notable":[14],"interest,":[15],"gradually":[16],"shifting":[17],"from":[18],"professional-generated":[19],"content":[20,24],"(PGC)":[21],"user-generated":[23],"(UGC).":[25],"However,":[26],"study":[28],"audio-visual":[30],"quality":[31],"assessment":[32],"(AVQA)":[33],"within":[34],"ODVs":[35],"remains":[36],"limited.":[37],"To":[38],"address":[39],"this,":[40],"we":[41,105],"construct":[42,106],"a":[43],"dataset":[44,83],"UGC":[46],"audio":[48,127],"and":[49,130],"video":[50,123],"(A/V)":[51],"content.":[52],"The":[53,134],"are":[55],"captured":[56],"by":[57],"five":[58],"individuals":[59],"using":[60],"two":[61],"different":[62,72],"types":[63],"cameras,":[66],"shooting":[67],"300":[68],"covering":[70],"10":[71],"scene":[73],"types.":[74],"A":[75],"subjective":[76],"AVQA":[77,103,109],"experiment":[78],"is":[79],"conducted":[80],"on":[81,112,144],"obtain":[85],"Mean":[87],"Opinion":[88],"Scores":[89],"(MOSs)":[90],"A/V":[93],"sequences.":[94],"After":[95],"that,":[96],"facilitate":[98],"development":[100],"UGC-ODV":[102],"fields,":[104],"an":[107],"effective":[108],"baseline":[110,119],"model":[111,120,140],"proposed":[114,146],"dataset,":[115],"which":[117],"consists":[121],"feature":[124,128],"extraction":[125,129],"module,":[126],"audiovisual":[131],"fusion":[132],"module.":[133],"experimental":[135],"results":[136],"demonstrate":[137],"that":[138],"our":[139],"achieves":[141],"optimal":[142],"performance":[143],"dataset.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}
