{"id":"https://openalex.org/W7131212263","doi":"https://doi.org/10.1109/vcip67698.2025.11396889","title":"CVBench: Benchmarking and Comparing Video Generation with Large Multimodal Models","display_name":"CVBench: Benchmarking and Comparing Video Generation with Large Multimodal Models","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131212263","doi":"https://doi.org/10.1109/vcip67698.2025.11396889"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126713264","display_name":"Jiarui Wang","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":"Jiarui Wang","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/A5126679174","display_name":"Huiyu Duan","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":"Huiyu Duan","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/A5113402572","display_name":"Yuke Xing","orcid":"https://orcid.org/0000-0002-7165-1615"},"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":"Yuke Xing","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/A5126675602","display_name":"Wei Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Cardiff University,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University,United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126740280","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":["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":"last","author":{"id":"https://openalex.org/A5126660745","display_name":"Xiongkuo Min","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":"Xiongkuo Min","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":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17569999396800995,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17569999396800995,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15469999611377716,"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/T12031","display_name":"Speech and dialogue systems","score":0.07739999890327454,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/benchmarking","display_name":"Benchmarking","score":0.8554999828338623},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7565000057220459},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7473000288009644},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7276999950408936},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49889999628067017},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.43959999084472656},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.34389999508857727},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8554999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904999852180481},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7565000057220459},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7473000288009644},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7276999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6226000189781189},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5774999856948853},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:185727","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/view/cardiffauthors/A2824239D.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2162915697","https://openalex.org/W2473697052","https://openalex.org/W2560703252","https://openalex.org/W2571248288","https://openalex.org/W2777280533","https://openalex.org/W2794680924","https://openalex.org/W2965644659","https://openalex.org/W3138516171","https://openalex.org/W3153469116","https://openalex.org/W3193919962","https://openalex.org/W4225292576","https://openalex.org/W4308772371","https://openalex.org/W4312818079","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4390874002","https://openalex.org/W4390874113","https://openalex.org/W4402660110","https://openalex.org/W4402727736","https://openalex.org/W4402753874","https://openalex.org/W4402916399","https://openalex.org/W4403792127","https://openalex.org/W4404784276","https://openalex.org/W4405695475","https://openalex.org/W4413158015","https://openalex.org/W4415797571"],"related_works":[],"abstract_inverted_index":{"Large":[0],"multimodal":[1],"models":[2,80,112],"(LMMs)":[3],"have":[4],"revolutionized":[5],"both":[6,95,109,140],"text-to-video":[7],"(T2V)":[8],"generation":[9,111],"and":[10,24,48,63,81,98,106,113,144,162],"video-to-text":[11],"(V2T)":[12],"interpretation.":[13],"However,":[14],"despite":[15],"these":[16],"advancements,":[17],"issues":[18],"such":[19],"as":[20],"imperfect":[21],"perceptual":[22,96],"quality":[23,97,131],"inconsistent":[25],"text-video":[26,99],"alignment":[27,154],"continue":[28],"to":[29],"limit":[30],"the":[31,61,141,159],"practical":[32],"deployment":[33],"of":[34,94,108],"AI-generated":[35],"videos":[36],"(AIGVs).":[37],"Consequently,":[38],"there":[39],"is":[40],"a":[41,45,123],"pressing":[42],"need":[43],"for":[44,53,67,136],"reliable":[46],"benchmark":[47],"automatic":[49],"evaluation":[50,107,126],"framework":[51],"tailored":[52],"AIGVs.":[54],"To":[55],"this":[56],"end,":[57],"we":[58,120],"propose":[59,121],"CVBench,":[60,119],"largest":[62],"most":[64],"comprehensive":[65],"dataset":[66,102,161],"Comparative":[68],"Video":[69],"Benchmarking,":[70],"including":[71],"60K":[72],"video":[73],"pairs":[74],"generated":[75],"by":[76],"30":[77],"state-of-the-art":[78,153],"T2V":[79,110],"600K":[82],"pairwise":[83,137],"comparisons":[84],"annotated":[85],"with":[86,155],"over":[87],"1.7":[88],"million":[89],"human":[90,156],"judgments":[91],"from":[92,133],"perspectives":[93,135],"correspondence.":[100],"This":[101],"enables":[103],"bidirectional":[104],"benchmarking":[105],"V2T":[114],"interpretation":[115],"models.":[116],"Based":[117],"on":[118],"VComp,":[122],"novel":[124],"LMM-based":[125],"metric":[127,164],"that":[128,150],"captures":[129],"fine-grained":[130],"differences":[132],"multiple":[134],"comparison":[138],"at":[139,168],"instance":[142],"level":[143],"model":[145],"level.":[146],"Extensive":[147],"experiments":[148],"show":[149],"VComp":[151,163],"achieves":[152],"preferences.":[157],"Both":[158],"CVBench":[160],"will":[165],"be":[166],"available":[167],"https://github.com/IntMeGroup/CVBench.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-25T00:00:00"}