{"id":"https://openalex.org/W7138457928","doi":"https://doi.org/10.1609/aaai.v40i15.38269","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","display_name":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138457928","doi":"https://doi.org/10.1609/aaai.v40i15.38269"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i15.38269","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38269","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38269/42231","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38269/42231","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129692661","display_name":"Shi-Xue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shi-Xue Zhang","raw_affiliation_strings":["University of Science and Technology Beijing, China\nTencent Technology (Shenzhen) Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, China\nTencent Technology (Shenzhen) Co. Ltd, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746396","display_name":"Hongfa Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfa Wang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, China\nTencent Technology (Shenzhen) Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, China\nTencent Technology (Shenzhen) Co. Ltd, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111028333","display_name":"Duojun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duojun Huang","raw_affiliation_strings":["Tencent Technology (Shenzhen) Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"Tencent Technology (Shenzhen) Co. Ltd, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712184","display_name":"Xin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Tencent Technology (Shenzhen) Co. Ltd, China"],"affiliations":[{"raw_affiliation_string":"Tencent Technology (Shenzhen) Co. Ltd, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124787294","display_name":"Xiaobin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Zhu","raw_affiliation_strings":["University of Science and Technology Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["University of Science and Technology Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129692661"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84850746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"12726","last_page":"12734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9550999999046326,"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":0.9550999999046326,"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":0.02160000056028366,"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":0.002400000113993883,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8465999960899353},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6771000027656555},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4893999993801117},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.45829999446868896},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39250001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514000177383423},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8465999960899353},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3919000029563904},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37470000982284546},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.35910001397132874},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i15.38269","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38269","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38269/42231","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i15.38269","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38269","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38269/42231","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5851750373840332,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138457928.pdf","grobid_xml":"https://content.openalex.org/works/W7138457928.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0,60],"captions":[1],"play":[2],"a":[3,121],"crucial":[4],"role":[5],"in":[6,34,44],"text-to-video":[7,100,142],"generation":[8],"tasks,":[9],"as":[10],"their":[11],"quality":[12,129],"directly":[13],"influences":[14],"the":[15,22,58,65,138],"semantic":[16],"coherence":[17],"and":[18,74,91,115],"visual":[19],"fidelity":[20],"of":[21,140],"generated":[23],"videos.":[24],"Although":[25],"large":[26,122],"vision-language":[27],"models":[28,143],"(VLMs)":[29],"have":[30],"demonstrated":[31],"significant":[32],"potential":[33],"caption":[35,128,149],"generation,":[36],"existing":[37],"benchmarks":[38],"inadequately":[39],"address":[40,53],"fine-grained":[41,68,86],"evaluation,":[42],"particularly":[43],"capturing":[45],"spatial-temporal":[46],"details":[47],"critical":[48,98],"for":[49,99,148],"video":[50],"generation.":[51,101],"To":[52],"this":[54],"gap,":[55],"we":[56],"introduce":[57,104],"Fine-grained":[59],"Caption":[61],"Evaluation":[62],"Benchmark":[63],"(VCapsBench),":[64],"first":[66],"large-scale":[67],"benchmark":[69,135],"comprising":[70],"5,677":[71],"(5K+)":[72],"videos":[73],"109,796":[75],"(100K+)":[76],"question-answer":[77],"pairs.":[78],"These":[79],"QA-pairs":[80,132],"are":[81,95],"systematically":[82],"annotated":[83],"across":[84],"21":[85],"dimensions":[87],"(e.g.,":[88],"camera":[89],"movement,":[90],"shot":[92],"type)":[93],"that":[94],"empirically":[96],"proven":[97],"We":[102],"further":[103],"three":[105],"metrics":[106],"(Accuracy":[107],"(AR),":[108],"Inconsistency":[109],"Rate":[110,113],"(IR),":[111],"Coverage":[112],"(CR)),":[114],"an":[116],"automated":[117],"evaluation":[118],"pipeline":[119],"leveraging":[120],"language":[123],"model":[124],"(LLM)":[125],"to":[126],"verify":[127],"via":[130],"contrastive":[131],"analysis.":[133],"Our":[134],"can":[136],"advance":[137],"development":[139],"robust":[141],"by":[144],"providing":[145],"actionable":[146],"insights":[147],"optimization.":[150]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}