{"id":"https://openalex.org/W4383750585","doi":"https://doi.org/10.1109/tip.2023.3290528","title":"Subjective and Objective Audio-Visual Quality Assessment for User Generated Content","display_name":"Subjective and Objective Audio-Visual Quality Assessment for User Generated Content","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383750585","doi":"https://doi.org/10.1109/tip.2023.3290528","pmid":"https://pubmed.ncbi.nlm.nih.gov/37428674"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3290528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3290528","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101983011","display_name":"Yuqin Cao","orcid":"https://orcid.org/0000-0002-5087-6559"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuqin Cao","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5087-6559","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5693-0416","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044700284","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0001-8162-1949"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8162-1949","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, and the Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, and the Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101983011"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.8857,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95057555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"3847","last_page":"3861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9937000274658203,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9905999898910522,"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":0.77574622631073},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7517907023429871},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5963695645332336},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4674661457538605},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.46530136466026306},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43066054582595825},{"id":"https://openalex.org/keywords/pevq","display_name":"PEVQ","score":0.4271647334098816},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3591442108154297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3569405674934387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33509349822998047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3279692530632019},{"id":"https://openalex.org/keywords/subjective-video-quality","display_name":"Subjective video quality","score":0.2787485122680664},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.1774657964706421},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12960484623908997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77574622631073},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7517907023429871},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5963695645332336},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4674661457538605},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.46530136466026306},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43066054582595825},{"id":"https://openalex.org/C156414586","wikidata":"https://www.wikidata.org/wiki/Q15995396","display_name":"PEVQ","level":5,"score":0.4271647334098816},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3591442108154297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3569405674934387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33509349822998047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3279692530632019},{"id":"https://openalex.org/C114227958","wikidata":"https://www.wikidata.org/wiki/Q7631422","display_name":"Subjective video quality","level":4,"score":0.2787485122680664},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.1774657964706421},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12960484623908997},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3290528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3290528","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:37428674","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37428674","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4054117750","display_name":null,"funder_award_id":"61831015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308688204","display_name":null,"funder_award_id":"2021YFE0206700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8668751174","display_name":null,"funder_award_id":"62225112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8830604195","display_name":null,"funder_award_id":"62271312","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W216108723","https://openalex.org/W1979451680","https://openalex.org/W1982471090","https://openalex.org/W1987489060","https://openalex.org/W2026139930","https://openalex.org/W2028192504","https://openalex.org/W2048042940","https://openalex.org/W2102166818","https://openalex.org/W2131774270","https://openalex.org/W2134963900","https://openalex.org/W2148848374","https://openalex.org/W2153635508","https://openalex.org/W2245625259","https://openalex.org/W2250384498","https://openalex.org/W2344658395","https://openalex.org/W2403022557","https://openalex.org/W2472977378","https://openalex.org/W2603172850","https://openalex.org/W2611434713","https://openalex.org/W2617811665","https://openalex.org/W2785586734","https://openalex.org/W2791258091","https://openalex.org/W2891639616","https://openalex.org/W2939995367","https://openalex.org/W2950154603","https://openalex.org/W2962858109","https://openalex.org/W2985767095","https://openalex.org/W2990391914","https://openalex.org/W3000351820","https://openalex.org/W3002992380","https://openalex.org/W3019533076","https://openalex.org/W3030701471","https://openalex.org/W3035595647","https://openalex.org/W3037131672","https://openalex.org/W3091249416","https://openalex.org/W3095348033","https://openalex.org/W3100404621","https://openalex.org/W3103745061","https://openalex.org/W3174089122","https://openalex.org/W3174722860","https://openalex.org/W3193919962","https://openalex.org/W3195201937","https://openalex.org/W4225292576","https://openalex.org/W4304098873","https://openalex.org/W4312606564","https://openalex.org/W4312624596","https://openalex.org/W4327662052","https://openalex.org/W4367146870","https://openalex.org/W4386590515","https://openalex.org/W6647225686","https://openalex.org/W6713708614","https://openalex.org/W6850847994"],"related_works":["https://openalex.org/W4388138958","https://openalex.org/W2041105906","https://openalex.org/W2611572988","https://openalex.org/W2061696964","https://openalex.org/W2067811204","https://openalex.org/W4385804965","https://openalex.org/W2345852733","https://openalex.org/W2126011296","https://openalex.org/W2046455617","https://openalex.org/W2149824261"],"abstract_inverted_index":{"In":[0,63],"recent":[1],"years,":[2],"User":[3],"Generated":[4],"Content":[5],"(UGC)":[6],"has":[7],"grown":[8],"dramatically":[9],"in":[10,232,253],"video":[11,21,101,165],"sharing":[12],"applications.":[13],"It":[14],"is":[15,113,258],"necessary":[16],"for":[17,202],"service-providers":[18],"to":[19,25,118,168,297],"use":[20],"quality":[22,55,74],"assessment":[23,75],"(VQA)":[24],"monitor":[26],"and":[27,80,100,155,164,187,207,217,249,278,287],"control":[28],"users'":[29],"Quality":[30],"of":[31,49,125,134,143,172,179,192,198,290],"Experience":[32],"when":[33],"watching":[34],"UGC":[35,40,72,88,98,235],"videos.":[36],"However,":[37],"most":[38],"existing":[39,262],"VQA":[41,158,215],"studies":[42],"only":[43],"focus":[44],"on":[45,58,71,115,182,274],"the":[46,53,59,86,106,116,120,126,131,135,144,162,170,183,194,213,254,269,275,288,291],"visual":[47,250],"distortions":[48],"videos,":[50,236],"ignoring":[51],"that":[52],"perceptual":[54],"also":[56],"depends":[57],"accompanying":[60],"audio":[61,99,163,218,248],"signals.":[62],"this":[64],"paper,":[65],"we":[66,84,138,175,237],"conduct":[67],"a":[68,140,177],"comprehensive":[69],"study":[70],"audio-visual":[73],"(AVQA)":[76],"from":[77,105,160],"both":[78,161],"subjective":[79,110],"objective":[81],"perspectives.":[82],"Specially,":[83],"construct":[85,176],"first":[87],"AVQA":[89,111,153,173,180,190,199,208,228,242,263,272,282],"database":[90,117,146,186,277,286],"named":[91],"SJTU-UAV":[92,136,145,185,276,285],"database,":[93,137,159],"which":[94,193,257],"includes":[95],"520":[96],"in-the-wild":[97,234],"(A/V)":[102],"sequences":[103,206],"collected":[104],"YFCC100m":[107],"database.":[108],"A":[109],"experiment":[112],"conducted":[114],"obtain":[119],"mean":[121],"opinion":[122],"scores":[123],"(MOSs)":[124],"A/V":[127,205],"sequences.":[128],"To":[129],"demonstrate":[130],"content":[132],"diversity":[133],"give":[139],"detailed":[141],"analysis":[142],"as":[147,149],"well":[148],"other":[150,188],"two":[151,189,279],"synthetically-distorted":[152],"databases":[154],"one":[156],"authentically-distorted":[157],"aspects.":[166],"Then,":[167],"facilitate":[169,298],"development":[171],"fields,":[174],"benchmark":[178,195,227,271],"models":[181,196,200,209,229,273],"proposed":[184,266,292],"databases,":[191],"consist":[197],"designed":[201],"synthetically":[203,280],"distorted":[204,281],"built":[210],"through":[211],"combining":[212],"popular":[214],"methods":[216],"features":[219],"via":[220,244],"support":[221],"vector":[222],"regressor":[223],"(SVR).":[224],"Finally,":[225],"considering":[226],"perform":[230],"poorly":[231],"assessing":[233],"further":[238,299],"propose":[239],"an":[240],"effective":[241],"model":[243,267,293],"jointly":[245],"learning":[246],"quality-aware":[247],"feature":[251],"representations":[252],"temporal":[255],"domain,":[256],"seldom":[259],"investigated":[260],"by":[261],"models.":[264],"Our":[265],"outperforms":[268],"aforementioned":[270],"databases.":[283],"The":[284],"code":[289],"will":[294],"be":[295],"released":[296],"research.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}