{"id":"https://openalex.org/W7128738784","doi":"https://doi.org/10.48448/je5a-qc46","title":"559 - VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","display_name":"559 - VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128738784","doi":"https://doi.org/10.48448/je5a-qc46"},"language":"en","primary_location":{"id":"doi:10.48448/je5a-qc46","doi":"https://doi.org/10.48448/je5a-qc46","is_oa":true,"landing_page_url":"https://doi.org/10.48448/je5a-qc46","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/je5a-qc46","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111028333","display_name":"Duojun Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Duojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125739849","display_name":"XIN LI","orcid":"https://orcid.org/0009-0007-0634-6685","observed_orcids":["https://orcid.org/0009-0007-0634-6685"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125766616","display_name":"Hongfa Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongfa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125717181","display_name":"Xu-Cheng Yin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Xu-Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125728189","display_name":"Shi-Xue Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shi-Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125712937","display_name":"Xiaobin Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiaobin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/video-captioning","display_name":"video captioning","score":0.8389999866485596},{"id":"https://openalex.org/keywords/text-to-video-generation","display_name":"text-to-video generation","score":0.8019999861717224},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7870000004768372},{"id":"https://openalex.org/keywords/question-answer-pairs","display_name":"question-answer pairs","score":0.6520000100135803},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.6209999918937683}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8600999712944031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8585000038146973},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6654000282287598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4936000108718872},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.42719998955726624},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3001999855041504},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/je5a-qc46","doi":"https://doi.org/10.48448/je5a-qc46","is_oa":true,"landing_page_url":"https://doi.org/10.48448/je5a-qc46","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/je5a-qc46","doi":"https://doi.org/10.48448/je5a-qc46","is_oa":true,"landing_page_url":"https://doi.org/10.48448/je5a-qc46","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128734434","https://openalex.org/W7168417912","https://openalex.org/W4407759813","https://openalex.org/W4416037265","https://openalex.org/W4416014890","https://openalex.org/W7216483814","https://openalex.org/W7103179791","https://openalex.org/W4415798317","https://openalex.org/W4402727496","https://openalex.org/W7214742136"],"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":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}