{"id":"https://openalex.org/W7135035865","doi":"https://doi.org/10.1109/tcsvt.2026.3673333","title":"Unveiling the Modular Design of Text-to-Video Quality Assessment","display_name":"Unveiling the Modular Design of Text-to-Video Quality Assessment","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135035865","doi":"https://doi.org/10.1109/tcsvt.2026.3673333"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3673333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3673333","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5076864270","display_name":"Bin Zheng","orcid":"https://orcid.org/0000-0003-3476-5936"},"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":"Bingkun Zheng","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128813418","display_name":"Weixia Zhang","orcid":null},"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":"Weixia Zhang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3634-2630","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128916661","display_name":"Guangtao Zhai","orcid":null},"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, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"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":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, 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":0,"citation_normalized_percentile":{"value":0.24190065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"10230","last_page":"10243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.22089999914169312,"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/T11439","display_name":"Video Analysis and Summarization","score":0.22089999914169312,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.15680000185966492,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.07180000096559525,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6111000180244446},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.45190000534057617},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.28690001368522644},{"id":"https://openalex.org/keywords/modular-construction","display_name":"Modular construction","score":0.28189998865127563}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5910000205039978},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.45190000534057617},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30329999327659607},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2777614354","wikidata":"https://www.wikidata.org/wiki/Q55648394","display_name":"Modular construction","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C55396564","wikidata":"https://www.wikidata.org/wiki/Q3084971","display_name":"Process design","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C138852830","wikidata":"https://www.wikidata.org/wiki/Q2292993","display_name":"Design methods","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C7166840","wikidata":"https://www.wikidata.org/wiki/Q1199682","display_name":"System testing","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3673333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3673333","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8250733612","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G8672032385","display_name":null,"funder_award_id":"62371283","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/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"generated":[2,28],"content":[3,44],"(AIGC)":[4],"are":[5],"reshaping":[6],"digital":[7],"media":[8],"creation,":[9],"with":[10,46],"text-to-video":[11],"(T2V)":[12],"generation":[13,206],"emerging":[14],"as":[15,37],"one":[16],"of":[17,53,80,111,145,190],"its":[18,191],"most":[19],"powerful":[20],"and":[21,43,99,128,138,143,180],"widely-used":[22],"techniques.":[23,207],"Despite":[24],"rapid":[25],"progress,":[26],"videos":[27,66],"by":[29,185],"T2V":[30,65,84,113,152,199,205],"models":[31,63,89,115,159],"still":[32],"suffer":[33],"from":[34,160,188],"issues":[35],"such":[36],"unrealistic":[38],"spatial":[39,122],"details,":[40],"temporal":[41,125],"inconsistencies,":[42],"misalignment":[45],"the":[47,108,140,157,203],"input":[48],"textual":[49],"prompts.":[50],"It":[51],"is":[52,174,211],"high":[54],"importance":[55],"to":[56,67,176,202],"develop":[57],"computational":[58],"video":[59],"quality":[60,78,85,120],"assessment":[61,86],"(VQA)":[62],"for":[64,73,197],"ensure":[68],"a":[69],"favorable":[70],"quality-of-experience":[71],"(QoE)":[72],"end":[74],"users.":[75],"Towards":[76],"comprehensive":[77],"evaluation":[79],"AI-generated":[81],"videos,":[82],"modern":[83,112],"(T2V":[87],"QA)":[88],"typically":[90],"integrate":[91],"multiple":[92,151],"modules":[93,110],"that":[94,156],"excel":[95],"in":[96],"capturing":[97],"different":[98],"complementary":[100],"quality-aware":[101],"features.":[102],"In":[103],"this":[104,133,161],"paper,":[105],"we":[106,135,154],"categorize":[107],"constituent":[109,192],"QA":[114,200],"into":[116],"four":[117],"types:":[118],"base":[119],"evaluators,":[121],"perception":[123,126],"modules,":[124,127,193],"text-video":[129],"alignment":[130],"modules.":[131],"Within":[132],"framework,":[134],"systematically":[136],"evaluate":[137],"compare":[139],"relative":[141],"strengths":[142],"weaknesses":[144],"candidate":[146],"models.":[147],"Through":[148],"experiments":[149],"on":[150],"datasets,":[153],"verify":[155],"top-performing":[158],"competition":[162],"demonstrate":[163],"very":[164],"competitive":[165],"performance":[166],"against":[167],"existing":[168],"VQA":[169],"methods.":[170],"The":[171],"resulting":[172],"framework":[173],"agnostic":[175],"specific":[177],"architectural":[178],"designs":[179],"can":[181],"be":[182],"continuously":[183],"refined":[184],"integrating":[186],"advancements":[187],"each":[189],"making":[194],"it":[195],"well-suited":[196],"adapting":[198],"methods":[201],"fast-evolving":[204],"Our":[208],"source":[209],"code":[210],"available":[212],"at":[213],"https://github.com/CH053N0N3/mineBVQA.":[214]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-03-13T00:00:00"}
