{"id":"https://openalex.org/W4414455542","doi":"https://doi.org/10.1109/iccv51701.2025.01978","title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-Grained Question Generation and Answering","display_name":"ETVA: Evaluation of Text-to-Video Alignment via Fine-Grained Question Generation and Answering","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414455542","doi":"https://doi.org/10.1109/iccv51701.2025.01978"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16867","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kaisi Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisi Guan","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084288655","display_name":"Zhengfeng Lai","orcid":"https://orcid.org/0000-0002-2984-7913"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengfeng Lai","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062292360","display_name":"Yuchong Sun","orcid":"https://orcid.org/0009-0004-6559-5620"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchong Sun","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703023","display_name":"Zhang Peng","orcid":"https://orcid.org/0000-0002-7153-3088"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062908102","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0003-2968-2888"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kieran Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kieran Liu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101856888","display_name":"Meng Cao","orcid":"https://orcid.org/0000-0003-2657-7142"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Cao","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101505570","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0001-6036-9035"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21651907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21299","last_page":"21309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962999820709229,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9902999997138977,"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/key","display_name":"Key (lock)","score":0.5680999755859375},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5514000058174133},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5437999963760376},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40700000524520874},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.3637000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649999856948853},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4138999879360199},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.16867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16867","pdf_url":"https://arxiv.org/pdf/2503.16867","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.16867","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16867","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.16867","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16867","pdf_url":"https://arxiv.org/pdf/2503.16867","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Precisely":[0],"evaluating":[1],"semantic":[2,64],"alignment":[3,19,29,144],"between":[4],"text":[5],"prompts":[6,62,149],"and":[7,55,94,150,171],"generated":[8,100],"videos":[9],"remains":[10],"a":[11,44,58,74,103,113,120,137,158],"challenge":[12],"in":[13],"Text-to-Video":[14,49],"(T2V)":[15],"Generation.":[16],"Existing":[17],"text-to-video":[18,143,164],"metrics":[20,129],"like":[21],"CLIPScore":[22],"only":[23,132],"generate":[24,68],"coarse-grained":[25],"scores":[26],"without":[27],"fine-grained":[28,52],"details,":[30],"failing":[31],"to":[32,67],"align":[33],"with":[34,124],"human":[35,125],"preference.":[36],"To":[37],"address":[38],"this":[39],"limitation,":[40],"we":[41,72,166],"propose":[42],"ETVA,":[43],"novel":[45],"Evaluation":[46],"method":[47],"of":[48,117,161],"Alignment":[50],"via":[51],"question":[53,80],"generation":[54],"answering.":[56],"First,":[57],"multi-agent":[59],"system":[60],"parses":[61],"into":[63],"scene":[65],"graphs":[66],"atomic":[69,152],"questions.":[70],"Then":[71],"design":[73],"knowledge-augmented":[75],"multi-stage":[76,104],"reasoning":[77,105],"framework":[78],"for":[79,142,176],"answering,":[81],"where":[82],"an":[83],"auxiliary":[84],"LLM":[85,97],"first":[86],"retrieves":[87],"relevant":[88],"common-sense":[89],"knowledge":[90],"(e.g.,":[91],"physical":[92],"laws),":[93],"then":[95],"video":[96],"answers":[98],"the":[99,174],"questions":[101,153],"through":[102],"mechanism.":[106],"Extensive":[107],"experiments":[108],"demonstrate":[109],"that":[110],"ETVA":[111],"achieves":[112],"Spearman's":[114],"correlation":[115,123],"coefficient":[116],"58.47,":[118],"showing":[119],"much":[121],"higher":[122],"judgment":[126],"than":[127],"existing":[128,163],"which":[130],"attain":[131],"31.0.":[133],"We":[134],"also":[135],"construct":[136],"comprehensive":[138],"benchmark":[139],"specifically":[140],"designed":[141],"evaluation,":[145],"featuring":[146],"2k":[147],"diverse":[148],"12k":[151],"spanning":[154],"10":[155],"categories.":[156],"Through":[157],"systematic":[159],"evaluation":[160],"15":[162],"models,":[165],"identify":[167],"their":[168],"key":[169],"capabilities":[170],"limitations,":[172],"paving":[173],"way":[175],"next-generation":[177],"T2V":[178],"generation.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}