{"id":"https://openalex.org/W4206488317","doi":"https://doi.org/10.1145/3469877.3490588","title":"Blindly Predict Image and Video Quality in the Wild","display_name":"Blindly Predict Image and Video Quality in the Wild","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4206488317","doi":"https://doi.org/10.1145/3469877.3490588"},"language":"en","primary_location":{"id":"doi:10.1145/3469877.3490588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","raw_type":"proceedings-article"},"type":"article","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/A5015737161","display_name":"Jiapeng Tang","orcid":"https://orcid.org/0009-0000-2939-0055"},"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":"Jiapeng Tang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, CN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827805","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0003-0832-6761"},"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":"Yi Fang","raw_affiliation_strings":["Shanghai Jiao Tong University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, CN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020634084","display_name":"Yu Dong","orcid":"https://orcid.org/0000-0003-1406-6310"},"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":"Yu Dong","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, CN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577089","display_name":"Rong Xie","orcid":"https://orcid.org/0000-0002-8261-5337"},"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":"Rong Xie","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028704757","display_name":"Xiao Gu","orcid":"https://orcid.org/0000-0002-3015-5818"},"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":"Xiao Gu","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, CN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":["Shanghai Jiao Tong University, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, CN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"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":"Li Song","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.1807598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9984999895095825,"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":0.9980999827384949,"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":0.7780469655990601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7074559926986694},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6661747097969055},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.659156858921051},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5998862385749817},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5802688598632812},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5657081007957458},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5652853846549988},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5539973378181458},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5053425431251526},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4590739905834198},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4531358778476715},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.4285475015640259},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.411079466342926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27648961544036865},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.10750651359558105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10173061490058899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780469655990601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7074559926986694},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6661747097969055},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.659156858921051},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5998862385749817},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5802688598632812},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5657081007957458},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5652853846549988},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5539973378181458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5053425431251526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4590739905834198},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4531358778476715},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.4285475015640259},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.411079466342926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27648961544036865},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.10750651359558105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10173061490058899},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469877.3490588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3490588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","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":42,"referenced_works":["https://openalex.org/W1562683879","https://openalex.org/W1977725648","https://openalex.org/W1982471090","https://openalex.org/W1994719915","https://openalex.org/W2048042940","https://openalex.org/W2068531098","https://openalex.org/W2074883210","https://openalex.org/W2106775624","https://openalex.org/W2108598243","https://openalex.org/W2117644767","https://openalex.org/W2141983208","https://openalex.org/W2148848374","https://openalex.org/W2162692770","https://openalex.org/W2163370434","https://openalex.org/W2250384498","https://openalex.org/W2320852756","https://openalex.org/W2368744241","https://openalex.org/W2473697052","https://openalex.org/W2539781702","https://openalex.org/W2563786098","https://openalex.org/W2597507805","https://openalex.org/W2611434713","https://openalex.org/W2735451741","https://openalex.org/W2736492128","https://openalex.org/W2789650830","https://openalex.org/W2791258091","https://openalex.org/W2888880110","https://openalex.org/W2905544033","https://openalex.org/W2950154603","https://openalex.org/W2963093735","https://openalex.org/W2963470893","https://openalex.org/W2965644659","https://openalex.org/W3016028173","https://openalex.org/W3034539499","https://openalex.org/W3034850705","https://openalex.org/W3034882073","https://openalex.org/W3035719652","https://openalex.org/W3035731588","https://openalex.org/W3099047215","https://openalex.org/W3100404621","https://openalex.org/W3174865552","https://openalex.org/W4247049427"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W1997117005","https://openalex.org/W2593689994"],"abstract_inverted_index":{"Emerging":[0],"interests":[1],"have":[2,24],"been":[3],"brought":[4],"to":[5,63,94,110,114,133,172],"blind":[6],"quality":[7,100,139,162,179],"assessment":[8],"for":[9,46,160,177],"images/videos":[10],"captured":[11],"in":[12,28,81,101,145,169],"the":[13,42,47,54,76,102,105,120,149],"wild,":[14],"known":[15],"as":[16],"in-the-wild":[17],"I/VQA.":[18],"Prior":[19],"deep":[20],"learning":[21,113],"based":[22],"approaches":[23],"achieved":[25],"considerable":[26],"progress":[27],"I/VQA,":[29],"but":[30],"are":[31],"intrinsically":[32],"troubled":[33],"with":[34],"two":[35],"issues.":[36],"Firstly,":[37],"most":[38],"existing":[39,68],"methods":[40,70,191],"fine-tune":[41],"image-classification-oriented":[43],"pre-trained":[44],"models":[45],"absence":[48],"of":[49,122,137],"large-scale":[50],"I/VQA":[51,58],"datasets.":[52],"However,":[53],"task":[55],"misalignment":[56],"between":[57],"and":[59,98,140,198],"image":[60,97,123,196],"classification":[61],"leads":[62],"degraded":[64],"generalization":[65],"performance.":[66],"Secondly,":[67],"VQA":[69],"directly":[71],"conduct":[72],"temporal":[73],"pooling":[74],"on":[75,192],"predicted":[77],"frame-wise":[78,174],"scores,":[79],"resulting":[80],"ambiguous":[82],"inter-frame":[83,167],"relation":[84],"modeling.":[85],"In":[86,104,148],"this":[87],"work,":[88],"we":[89,108,126,152],"propose":[90,127],"a":[91,128,154],"two-stage":[92],"architecture":[93],"separately":[95],"predict":[96],"video":[99,161,199],"wild.":[103],"first":[106],"stage,":[107,151],"resort":[109],"supervised":[111],"contrastive":[112,131],"derive":[115],"quality-aware":[116,130],"representations":[117],"that":[118,184],"facilitate":[119],"prediction":[121],"quality.":[124],"Specifically,":[125],"novel":[129],"loss":[132],"pull":[134],"together":[135],"samples":[136],"similar":[138],"push":[141],"away":[142],"quality-different":[143],"ones":[144],"embedding":[146,170],"space.":[147],"second":[150],"develop":[153],"Relation-Guided":[155],"Temporal":[156],"Attention":[157],"(RTA)":[158],"module":[159],"prediction,":[163],"which":[164],"captures":[165],"global":[166],"dependencies":[168],"space":[171],"learn":[173],"attention":[175],"weights":[176],"frame":[178],"aggregation.":[180],"Extensive":[181],"experiments":[182],"demonstrate":[183],"our":[185],"approach":[186],"performs":[187],"favorably":[188],"against":[189],"state-of-the-art":[190],"both":[193],"authentically":[194],"distorted":[195],"benchmarks":[197],"benchmarks.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}