{"id":"https://openalex.org/W7166834561","doi":"https://doi.org/10.18653/v1/2026.acl-long.777","title":"Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering","display_name":"Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166834561","doi":"https://doi.org/10.18653/v1/2026.acl-long.777"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.777","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.777","pdf_url":"https://aclanthology.org/2026.acl-long.777.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.777.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139782024","display_name":"Zizhen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zizhen Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139716620","display_name":"Bo Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727754","display_name":"Zhengfeng Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengfeng Lai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809766","display_name":"Shiyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730190","display_name":"Yang Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139742039","display_name":"Meng Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139726865","display_name":"Ping Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139852870","display_name":"Xiaoming Simon Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoming Simon Wang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84305347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17079","last_page":"17099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9781000018119812,"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":0.9781000018119812,"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/T11439","display_name":"Video Analysis and Summarization","score":0.004699999932199717,"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":0.004000000189989805,"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/question-answering","display_name":"Question answering","score":0.6862999796867371},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6226999759674072},{"id":"https://openalex.org/keywords/ping","display_name":"Ping (video games)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4300000071525574},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.39579999446868896},{"id":"https://openalex.org/keywords/questions-and-answers","display_name":"Questions and answers","score":0.32330000400543213}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6862999796867371},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5771999955177307},{"id":"https://openalex.org/C156308498","wikidata":"https://www.wikidata.org/wiki/Q1347898","display_name":"Ping (video games)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3481999933719635},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C3018615553","wikidata":"https://www.wikidata.org/wiki/Q189293","display_name":"Frequently asked questions","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.777","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.777","pdf_url":"https://aclanthology.org/2026.acl-long.777.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.777","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.777","pdf_url":"https://aclanthology.org/2026.acl-long.777.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8281582593917847,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166834561.pdf","grobid_xml":"https://content.openalex.org/works/W7166834561.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zizhen":[0],"Wang,":[1],"Bo":[2],"Feng,":[3],"Zhengfeng":[4],"Lai,":[5],"Shiyu":[6],"Li,":[7],"Yang":[8],"Lu,":[9],"Meng":[10],"Cao,":[11],"Ping":[12],"Huang,":[13],"Xiaoming":[14],"Simon":[15],"Wang.":[16],"Proceedings":[17],"of":[18,23],"the":[19,24],"64th":[20],"Annual":[21],"Meeting":[22],"Association":[25],"for":[26],"Computational":[27],"Linguistics":[28],"(Volume":[29],"1:":[30],"Long":[31],"Papers).":[32],"2026.":[33]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}
