{"id":"https://openalex.org/W4416037265","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.59","title":"VC4VG: Optimizing Video Captions for Text-to-Video Generation","display_name":"VC4VG: Optimizing Video Captions for Text-to-Video Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037265","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.59"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.59","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.59","pdf_url":"https://aclanthology.org/2025.emnlp-main.59.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.59.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011136999","display_name":"Yang Du","orcid":"https://orcid.org/0000-0002-5707-513X"},"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":"Yang Du","raw_affiliation_strings":["School of Information , Renmin University of China ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information , Renmin University of China ,","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053192190","display_name":"Zhuoran Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Lin","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083752471","display_name":"Kaiqiang Song","orcid":"https://orcid.org/0000-0001-8203-9723"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqiang Song","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439512","display_name":"Biao Wang","orcid":"https://orcid.org/0000-0003-4656-8278"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biao Wang","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003590362","display_name":"Zhicheng Zheng","orcid":"https://orcid.org/0000-0002-9235-9074"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhicheng Zheng","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027308029","display_name":"Tiezheng Ge","orcid":"https://orcid.org/0000-0003-1381-2692"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiezheng Ge","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050479679","display_name":"B. Zheng","orcid":"https://orcid.org/0000-0002-6544-429X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"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":"Qin Jin","raw_affiliation_strings":["School of Information , Renmin University of China ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information , Renmin University of China ,","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.35162504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1124","last_page":"1138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5408999919891357,"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":0.5408999919891357,"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":0.21209999918937683,"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":0.0803999975323677,"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/closed-captioning","display_name":"Closed captioning","score":0.27230000495910645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26330000162124634},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.2563000023365021},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.24240000545978546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2345999926328659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272000074386597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45190000534057617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.24240000545978546},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.23559999465942383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2345999926328659},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.22930000722408295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.59","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.59","pdf_url":"https://aclanthology.org/2025.emnlp-main.59.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.59","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.59","pdf_url":"https://aclanthology.org/2025.emnlp-main.59.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037265.pdf","grobid_xml":"https://content.openalex.org/works/W4416037265.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,14],"text-to-video":[3],"(T2V)":[4],"generation":[5,115],"highlight":[6],"the":[7,52,67,118],"critical":[8],"role":[9],"of":[10,18,54,120],"highquality":[11],"video-text":[12],"pairs":[13],"training":[15,32],"models":[16],"capable":[17],"producing":[19],"coherent":[20],"and":[21,77,95,113,127],"instructionaligned":[22],"videos.However,":[23],"strategies":[24],"for":[25,30,42,71],"optimizing":[26],"video":[27,72,114],"captions":[28],"specifically":[29],"T2V":[31,55,64,102],"remain":[33],"underexplored.In":[34],"this":[35],"paper,":[36],"we":[37,86],"introduce":[38],"VC4VG":[39],"(Video":[40],"Captioning":[41],"Video":[43],"Generation),":[44],"a":[45,63,79,89,106],"comprehensive":[46],"caption":[47,60,81,111],"optimization":[48],"framework":[49],"tailored":[50],"to":[51,130],"needs":[53],"models.We":[56],"begin":[57],"by":[58],"analyzing":[59],"content":[61],"from":[62],"perspective,":[65],"decomposing":[66],"essential":[68],"elements":[69],"required":[70],"reconstruction":[73],"into":[74],"multiple":[75],"dimensions,":[76],"proposing":[78],"principled":[80],"design":[82],"methodology.To":[83],"support":[84,131],"evaluation,":[85],"construct":[87],"VC4VG-Bench,":[88],"new":[90],"benchmark":[91,125],"featuring":[92],"fine-grained,":[93],"multi-dimensional,":[94],"necessity-graded":[96],"metrics":[97],"aligned":[98],"with":[99],"T2Vspecific":[100],"requirements.Extensive":[101],"finetuning":[103],"experiments":[104],"demonstrate":[105],"strong":[107],"correlation":[108],"between":[109],"improved":[110],"quality":[112],"performance,":[116],"validating":[117],"effectiveness":[119],"our":[121],"approach.We":[122],"release":[123],"all":[124],"tools":[126],"code":[128],"1":[129],"further":[132],"research.":[133]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-11-08T00:00:00"}