{"id":"https://openalex.org/W4385474549","doi":"https://doi.org/10.48550/arxiv.2307.16813","title":"Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment","display_name":"Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment","publication_year":2023,"publication_date":"2023-07-31","ids":{"openalex":"https://openalex.org/W4385474549","doi":"https://doi.org/10.48550/arxiv.2307.16813"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.16813","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.16813","pdf_url":"https://arxiv.org/pdf/2307.16813","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.16813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100614601","display_name":"Kun Yuan","orcid":"https://orcid.org/0000-0002-3681-2196"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuan, Kun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055726533","display_name":"Zishang Kong","orcid":"https://orcid.org/0000-0001-7194-8198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Zishang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017940741","display_name":"Chuanchuan Zheng","orcid":"https://orcid.org/0000-0002-3617-2184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Chuanchuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102998429","display_name":"Ming Sun","orcid":"https://orcid.org/0009-0002-6753-3568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101229875","display_name":"Xing Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Xing","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100614601"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9995999932289124,"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":0.9995999932289124,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.989799976348877,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7059788703918457},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5457784533500671},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5448030233383179},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5281060934066772},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5064016580581665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41941964626312256},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4107726812362671},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18079209327697754},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.1312466859817505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059788703918457},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5457784533500671},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5448030233383179},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5281060934066772},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5064016580581665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41941964626312256},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4107726812362671},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18079209327697754},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.1312466859817505},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.16813","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.16813","pdf_url":"https://arxiv.org/pdf/2307.16813","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.16813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.16813","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:2307.16813","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.16813","pdf_url":"https://arxiv.org/pdf/2307.16813","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385474549.pdf","grobid_xml":"https://content.openalex.org/works/W4385474549.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4250539519","https://openalex.org/W2628861693","https://openalex.org/W4294018197","https://openalex.org/W3203087560","https://openalex.org/W4233433299","https://openalex.org/W4361279463","https://openalex.org/W2483824227","https://openalex.org/W1638319263","https://openalex.org/W1981278479","https://openalex.org/W4241962800"],"abstract_inverted_index":{"Video":[0],"Quality":[1,124],"Assessment":[2],"(VQA),":[3],"which":[4,152],"aims":[5],"to":[6,101,116,127,142,159],"predict":[7],"the":[8,19,70,74,90,102,105,118,147,154],"perceptual":[9,71,91],"quality":[10,72,92],"of":[11,22,73,84,93,109,176],"a":[12,94,97,135,164,184],"video,":[13,76],"has":[14],"attracted":[15],"raising":[16],"attention":[17],"with":[18,35,173],"rapid":[20],"development":[21],"streaming":[23],"media":[24],"technology,":[25],"such":[26],"as":[27],"Facebook,":[28],"TikTok,":[29],"Kwai,":[30],"and":[31,107,217],"so":[32],"on.":[33],"Compared":[34],"other":[36,78],"sequence-based":[37,79],"visual":[38],"tasks":[39,80],"(\\textit{e.g.,}":[40],"action":[41],"recognition),":[42],"VQA":[43,199,209],"faces":[44],"two":[45],"under-estimated":[46],"challenges":[47],"unresolved":[48],"in":[49,104,178,183,195,206],"User":[50],"Generated":[51],"Content":[52],"(UGC)":[53],"videos.":[54],"\\textit{First},":[55],"it":[56],"is":[57,140],"not":[58],"rare":[59],"that":[60],"several":[61],"frames":[62,83],"containing":[63],"serious":[64],"distortions":[65,182],"(\\textit{e.g.,}blocking,":[66],"blurriness),":[67],"can":[68],"determine":[69],"whole":[75],"while":[77],"require":[81],"more":[82,132],"equal":[85],"importance":[86],"for":[87,111],"representations.":[88],"\\textit{Second},":[89],"video":[95],"exhibits":[96],"multi-distortion":[98],"distribution,":[99],"due":[100],"differences":[103],"duration":[106],"probability":[108],"occurrence":[110],"various":[112],"distortions.":[113],"In":[114],"order":[115],"solve":[117],"above":[119],"challenges,":[120],"we":[121],"propose":[122],"\\textit{Visual":[123],"Transformer":[125],"(VQT)}":[126],"extract":[128],"quality-related":[129],"sparse":[130],"features":[131],"efficiently.":[133],"Methodologically,":[134],"Sparse":[136],"Temporal":[137,166],"Attention":[138],"(STA)":[139],"proposed":[141],"sample":[143],"keyframes":[144],"by":[145],"analyzing":[146],"temporal":[148],"correlation":[149],"between":[150],"frames,":[151],"reduces":[153],"computational":[155],"complexity":[156],"from":[157],"$O(T^2)$":[158],"$O(T":[160],"\\log":[161],"T)$.":[162],"Structurally,":[163],"Multi-Pathway":[165],"Network":[167],"(MPTN)":[168],"utilizes":[169],"multiple":[170],"STA":[171],"modules":[172],"different":[174],"degrees":[175],"sparsity":[177],"parallel,":[179],"capturing":[180],"co-existing":[181],"video.":[185],"Experimentally,":[186],"VQT":[187,202],"demonstrates":[188],"superior":[189],"performance":[190,205],"than":[191],"many":[192],"\\textit{state-of-the-art}":[193],"methods":[194],"three":[196],"public":[197],"no-reference":[198],"datasets.":[200],"Furthermore,":[201],"shows":[203],"better":[204],"four":[207],"full-reference":[208],"datasets":[210],"against":[211],"widely-adopted":[212],"industrial":[213],"algorithms":[214],"(\\textit{i.e.,}":[215],"VMAF":[216],"AVQT).":[218]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2023-08-02T00:00:00"}