{"id":"https://openalex.org/W4415278952","doi":"https://doi.org/10.1145/3774904.3792726","title":"CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation","display_name":"CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W4415278952","doi":"https://doi.org/10.1145/3774904.3792726"},"language":"en","primary_location":{"id":"doi:10.1145/3774904.3792726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792726","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068039769","display_name":"Kaiwen Wei","orcid":"https://orcid.org/0000-0002-5830-0802"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Wei","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-5830-0802","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Liu","orcid":"https://orcid.org/0009-0005-0233-7410"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0005-0233-7410","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-0263-5037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Independent Researcher, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0263-5037","affiliations":[{"raw_affiliation_string":"Independent Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zijian Wang","orcid":"https://orcid.org/0009-0005-3598-4841"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Wang","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0005-3598-4841","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530367","display_name":"Ruida Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruida Liu","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0005-4864-2795","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100958962","display_name":"Yuming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Yang","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0002-5000-7609","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018898834","display_name":"Xin Xiao","orcid":"https://orcid.org/0009-0008-2846-6749"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xiao","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0008-2846-6749","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Sun","orcid":"https://orcid.org/0009-0007-7256-4357"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Sun","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0007-7256-4357","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyang Zeng","orcid":"https://orcid.org/0009-0000-9810-5684"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Zeng","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0000-9810-5684","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023331304","display_name":"Changzai Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changzai Pan","raw_affiliation_strings":["Independent Researcher, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-2676-9223","affiliations":[{"raw_affiliation_string":"Independent Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yidan Zhang","orcid":"https://orcid.org/0000-0002-7466-0234"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Zhang","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7466-0234","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang Zhong","orcid":"https://orcid.org/0000-0002-5169-4634"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Zhong","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-5169-4634","affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046600276","display_name":"Peijin Wang","orcid":"https://orcid.org/0000-0002-0371-5584"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peijin Wang","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0371-5584","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055032051","display_name":"Yingchao Feng","orcid":"https://orcid.org/0000-0003-4017-8885"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchao Feng","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4017-8885","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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":"2501","last_page":"2512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9936000108718872,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8230000138282776},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5489000082015991},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4936000108718872},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4779999852180481},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36469998955726624},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.32760000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8592000007629395},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8230000138282776},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508899986743927},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2646999955177307}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792726","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.09266","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09266","pdf_url":"https://arxiv.org/pdf/2510.09266","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.09266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.09266","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":"doi:10.1145/3774904.3792726","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792726","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,5],"Retrieval-Augmented":[1],"Generation":[2],"(MRAG)":[3],"enables":[4],"Large":[6],"Language":[7],"Models":[8],"(MLLMs)":[9],"to":[10,25,98,135],"generate":[11],"responses":[12],"with":[13],"external":[14,164],"multimodal":[15,110,141,175],"evidence.":[16],"Recently,":[17],"numerous":[18],"video-based":[19],"MRAG":[20],"benchmarks":[21,38],"have":[22],"been":[23],"proposed":[24],"evaluate":[26,116],"model":[27],"capabilities":[28],"across":[29,180],"retrieval":[30,118],"and":[31,44,85,93,100,120,161,177],"generation":[32],"stages":[33],"in":[34,41],"MRAG.":[35],"However,":[36],"existing":[37],"remain":[39],"limited":[40],"modality":[42],"coverage":[43],"format":[45],"diversity,":[46],"often":[47],"focusing":[48],"on":[49],"single-":[50],"or":[51,54,132],"limited-modality":[52],"tasks,":[53],"coarse-grained":[55],"scene":[56],"understanding.":[57],"To":[58,143],"address":[59],"these":[60],"gaps,":[61],"we":[62,114,146],"introduce":[63],"CFVBench,":[64,81,113],"a":[65,125,152],"large-scale,":[66],"manually":[67],"verified":[68],"benchmark":[69],"constructed":[70],"from":[71],"599":[72],"publicly":[73],"available":[74],"videos,":[75],"yielding":[76],"5,360":[77],"open-ended":[78],"QA":[79],"pairs.":[80],"spans":[82,106],"high-density":[83],"formats":[84],"domains":[86],"such":[87],"as":[88],"chart-heavy":[89],"reports,":[90],"news":[91],"broadcasts,":[92],"software":[94],"tutorials,":[95],"requiring":[96],"models":[97,129],"retrieve":[99],"reason":[101],"over":[102],"long":[103],"temporal":[104],"video":[105],"while":[107],"maintaining":[108],"fine-grained":[109,140,174],"information.":[111],"Using":[112],"systematically":[115],"7":[117],"methods":[119],"14":[121],"widely-used":[122],"MLLMs,":[123],"revealing":[124],"critical":[126],"bottleneck:":[127],"current":[128],"(even":[130],"GPT5":[131],"Gemini)":[133],"struggle":[134],"capture":[136],"transient":[137],"yet":[138],"essential":[139],"details.":[142],"mitigate":[144],"this,":[145],"propose":[147],"Adaptive":[148],"Visual":[149],"Refinement":[150],"(AVR),":[151],"plug-and-paly":[153],"framework":[154],"that":[155,170],"adaptively":[156],"increases":[157],"frame":[158],"sampling":[159],"density":[160],"selectively":[162],"invokes":[163],"tools":[165],"when":[166],"necessary.":[167],"Experiments":[168],"show":[169],"AVR":[171],"consistently":[172],"enhances":[173],"comprehension":[176],"improves":[178],"performance":[179],"all":[181],"evaluated":[182],"MLLMs.":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-17T00:00:00"}