{"id":"https://openalex.org/W4416159150","doi":"https://doi.org/10.1109/wacv61042.2026.00203","title":"CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video","display_name":"CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416159150","doi":"https://doi.org/10.1109/wacv61042.2026.00203"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.07290","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100382952","display_name":"Xinyi Wang","orcid":"https://orcid.org/0000-0002-6926-5934"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinyi Wang","raw_affiliation_strings":["University of Bristol,School of Computer Science,Bristol,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol,School of Computer Science,Bristol,United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053336934","display_name":"Angeliki Katsenou","orcid":"https://orcid.org/0000-0003-0081-4488"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Angeliki Katsenou","raw_affiliation_strings":["University of Bristol,School of Computer Science,Bristol,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol,School of Computer Science,Bristol,United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399628","display_name":"Junxiao Shen","orcid":"https://orcid.org/0000-0002-1552-4689"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junxiao Shen","raw_affiliation_strings":["University of Bristol,School of Computer Science,Bristol,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol,School of Computer Science,Bristol,United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048009053","display_name":"David Bull","orcid":"https://orcid.org/0000-0001-7634-190X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Bull","raw_affiliation_strings":["University of Bristol,School of Computer Science,Bristol,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol,School of Computer Science,Bristol,United Kingdom","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01384058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2042","last_page":"2051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9850999712944031,"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":0.9850999712944031,"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/T11439","display_name":"Video Analysis and Summarization","score":0.003599999938160181,"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":0.0034000000450760126,"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/metadata","display_name":"Metadata","score":0.6100999712944031},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5830000042915344},{"id":"https://openalex.org/keywords/transcoding","display_name":"Transcoding","score":0.5126000046730042},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44350001215934753},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4426000118255615},{"id":"https://openalex.org/keywords/subjective-video-quality","display_name":"Subjective video quality","score":0.4246000051498413},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41690000891685486},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.39809998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360999822616577},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5830000042915344},{"id":"https://openalex.org/C134535813","wikidata":"https://www.wikidata.org/wiki/Q1888734","display_name":"Transcoding","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45660001039505005},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4426000118255615},{"id":"https://openalex.org/C114227958","wikidata":"https://www.wikidata.org/wiki/Q7631422","display_name":"Subjective video quality","level":4,"score":0.4246000051498413},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.37549999356269836},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.30889999866485596},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C18446390","wikidata":"https://www.wikidata.org/wiki/Q273902","display_name":"MPEG-2","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.07290","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07290","pdf_url":"https://arxiv.org/pdf/2511.07290","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.07290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.07290","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.07290","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07290","pdf_url":"https://arxiv.org/pdf/2511.07290","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416159150.pdf","grobid_xml":"https://content.openalex.org/works/W4416159150.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,218],"prevalence":[1],"of":[2,30,37,60,72,76,96,173,204],"user-generated":[3],"content":[4,65],"(UGC)":[5],"on":[6,40,169],"platforms":[7,42],"such":[8],"as":[9],"YouTube":[10],"and":[11,33,151,159,207,221],"TikTok":[12],"has":[13,137],"rendered":[14],"no-reference":[15],"(NR)":[16],"perceptual":[17,74,142],"video":[18,25,39,109,164],"quality":[19,132,143,165],"assessment":[20],"(VQA)":[21],"vital":[22],"for":[23,46,63,191],"optimizing":[24],"delivery.":[26],"Nonetheless,":[27],"the":[28,34,70,92,125,189,199],"characteristics":[29],"non-professional":[31],"acquisition":[32],"subsequent":[35],"transcoding":[36],"UGC":[38,174],"sharing":[41],"present":[43],"significant":[44],"challenges":[45],"NR-VQA.":[47],"Although":[48],"NR-VQA":[49,88,183],"models":[50],"attempt":[51],"to":[52,69,123,140,163,215],"infer":[53],"mean":[54],"opinion":[55],"scores":[56,62],"(MOS),":[57],"their":[58],"modeling":[59],"subjective":[61],"compressed":[64],"remains":[66],"limited":[67],"due":[68],"absence":[71],"fine-grained":[73,131,194],"annotations":[75],"artifact":[77],"types.":[78],"To":[79],"address":[80],"these":[81],"challenges,":[82],"we":[83],"propose":[84],"CAMP-VQA,":[85],"a":[86,103,170,226],"novel":[87],"framework":[89],"that":[90,107,177],"exploits":[91],"semantic":[93,147],"understanding":[94],"capabilities":[95],"large":[97],"vision-language":[98],"models.":[99],"Our":[100,196],"approach":[101,128],"introduces":[102],"quality-aware":[104],"prompting":[105],"mechanism":[106],"integrates":[108],"metadata":[110],"(e.g.,":[111],"resolution,":[112],"frame":[113],"rate,":[114],"bitrate)":[115],"with":[116,225],"key":[117],"fragments":[118],"extracted":[119,158],"from":[120],"inter-frame":[121],"variations":[122],"guide":[124],"BLIP-2":[126],"pretraining":[127],"in":[129,202],"generating":[130],"captions.":[133],"A":[134],"unified":[135],"architecture":[136],"been":[138],"designed":[139],"model":[141,179],"across":[144],"three":[145],"dimensions:":[146],"alignment,":[148],"temporal":[149],"characteristics,":[150],"spatial":[152],"characteristics.":[153],"These":[154],"multimodal":[155],"features":[156],"are":[157,229],"fused,":[160],"then":[161],"regressed":[162],"scores.":[166],"Extensive":[167],"experiments":[168],"wide":[171],"variety":[172],"datasets":[175],"demonstrate":[176],"our":[178],"consistently":[180],"outperforms":[181],"existing":[182],"methods,":[184],"achieving":[185],"improved":[186],"accuracy":[187],"without":[188],"need":[190],"costly":[192],"manual":[193],"annotations.":[195],"method":[197],"achieves":[198],"best":[200],"performance":[201],"terms":[203],"average":[205],"rank":[206],"linear":[208],"correlation":[209],"(SRCC:":[210],"0.928,":[211],"PLCC:":[212],"0.938)":[213],"compared":[214],"state-of-the-art":[216],"methods.":[217],"source":[219],"code":[220],"trained":[222],"models,":[223],"along":[224],"user-friendly":[227],"demo,":[228],"available":[230],"at:":[231],"https://github.com/xinyiW915/CAMP-VQA.":[232]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-11-12T00:00:00"}