{"id":"https://openalex.org/W2989322838","doi":"https://doi.org/10.1109/iccv.2019.00468","title":"VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","display_name":"VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2989322838","doi":"https://doi.org/10.1109/iccv.2019.00468","mag":"2989322838"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.00468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040308771","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-5132-4465"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Wang","raw_affiliation_strings":["University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009633508","display_name":"Jiawei Wu","orcid":"https://orcid.org/0000-0001-6251-2202"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Wu","raw_affiliation_strings":["University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junkun Chen","raw_affiliation_strings":["ByteDance AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["ByteDance AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084077301","display_name":"Yuan\u2010Fang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan-Fang Wang","raw_affiliation_strings":["University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702485","display_name":"William Yang Wang","orcid":"https://orcid.org/0000-0001-6153-8240"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Yang Wang","raw_affiliation_strings":["University of California, Santa Barbara, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040308771"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":17.2659,"has_fulltext":false,"cited_by_count":443,"citation_normalized_percentile":{"value":0.99307975,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4580","last_page":"4590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9954000115394592,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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/closed-captioning","display_name":"Closed captioning","score":0.9159051179885864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.887161374092102},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.685617983341217},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6511741876602173},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6137424111366272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4952189028263092},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46293964982032776},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4162417948246002},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41181686520576477},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14957597851753235}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9159051179885864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887161374092102},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.685617983341217},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6511741876602173},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6137424111366272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952189028263092},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46293964982032776},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4162417948246002},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41181686520576477},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14957597851753235},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2019.00468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":96,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W589318051","https://openalex.org/W1488163396","https://openalex.org/W1572567476","https://openalex.org/W1588242179","https://openalex.org/W1596841185","https://openalex.org/W1773149199","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1927052826","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1995820507","https://openalex.org/W2064675550","https://openalex.org/W2078238240","https://openalex.org/W2080873731","https://openalex.org/W2086842362","https://openalex.org/W2101105183","https://openalex.org/W2111078031","https://openalex.org/W2126579184","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2251496547","https://openalex.org/W2258532548","https://openalex.org/W2337252826","https://openalex.org/W2341242007","https://openalex.org/W2425121537","https://openalex.org/W2508429489","https://openalex.org/W2509282593","https://openalex.org/W2513263213","https://openalex.org/W2553522418","https://openalex.org/W2563717578","https://openalex.org/W2572792611","https://openalex.org/W2581101319","https://openalex.org/W2619947201","https://openalex.org/W2652651782","https://openalex.org/W2749708282","https://openalex.org/W2760425631","https://openalex.org/W2784025607","https://openalex.org/W2797191581","https://openalex.org/W2849425149","https://openalex.org/W2889545026","https://openalex.org/W2891939431","https://openalex.org/W2899274165","https://openalex.org/W2903343986","https://openalex.org/W2914699769","https://openalex.org/W2952132648","https://openalex.org/W2962869524","https://openalex.org/W2962937869","https://openalex.org/W2962994439","https://openalex.org/W2963017553","https://openalex.org/W2963082528","https://openalex.org/W2963177403","https://openalex.org/W2963293463","https://openalex.org/W2963327853","https://openalex.org/W2963331233","https://openalex.org/W2963360627","https://openalex.org/W2963407669","https://openalex.org/W2963524571","https://openalex.org/W2963527096","https://openalex.org/W2963909453","https://openalex.org/W2963916161","https://openalex.org/W2964003477","https://openalex.org/W2964192290","https://openalex.org/W2964308564","https://openalex.org/W2964335490","https://openalex.org/W3101533854","https://openalex.org/W3102566412","https://openalex.org/W3104279398","https://openalex.org/W3104915307","https://openalex.org/W4297780100","https://openalex.org/W6600983433","https://openalex.org/W6629203210","https://openalex.org/W6634126550","https://openalex.org/W6635158094","https://openalex.org/W6639432524","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6692379709","https://openalex.org/W6729887601","https://openalex.org/W6732287329","https://openalex.org/W6739682802","https://openalex.org/W6747866816","https://openalex.org/W6753290298","https://openalex.org/W6755559483","https://openalex.org/W6785803246","https://openalex.org/W6785951546","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W2547835662","https://openalex.org/W1484029852","https://openalex.org/W3198474835","https://openalex.org/W2985347586","https://openalex.org/W4288023470","https://openalex.org/W2963442512","https://openalex.org/W3082735059","https://openalex.org/W3045475294"],"abstract_inverted_index":{"We":[0,64],"present":[1],"a":[2,82,88,100,139],"new":[3],"large-scale":[4],"multilingual":[5,127],"video":[6,59,83,110,140,158],"description":[7,103],"dataset,":[8],"VATEX":[9,46,120],"<sup":[10],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[11],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[12],",":[13],"which":[14],"contains":[15],"over":[16,33,148],"41,250":[17],"videos":[18],"and":[19,26,52,60,93,135,167,170],"825,":[20],"000":[21],"captions":[22],"in":[23,55,84],"both":[24,58,133],"English":[25,134],"Chinese.":[27],"Among":[28],"the":[29,41,105,109,119,125,149,156,176,180],"captions,":[30],"there":[31],"are":[32],"206,000":[34],"English-Chinese":[35],"parallel":[36],"translation":[37],"pairs.":[38],"Compared":[39],"to":[40,98,164],"widely-used":[42],"MSRVTT":[43],"dataset":[44,121],"[64],":[45],"is":[47],"multilingual,":[48],"larger,":[49],"linguistically":[50],"complex,":[51],"more":[53,141],"diverse":[54],"terms":[56],"of":[57,182],"natural":[61],"language":[62,102,107],"descriptions.":[63],"also":[65,144],"introduce":[66],"two":[67],"tasks":[68],"for":[69,138],"video-and-language":[70,186],"research":[71],"based":[72],"on":[73,118],"VATEX:":[74],"(1)":[75],"Multilingual":[76],"Video":[77],"Captioning,":[78],"aimed":[79],"at":[80],"describing":[81],"various":[85],"languages":[86,169],"with":[87],"compact":[89],"unified":[90,126],"captioning":[91],"model,":[92],"(2)":[94],"Video-guided":[95],"Machine":[96],"Translation,":[97],"translate":[99],"source":[101,166],"into":[104],"target":[106,168],"using":[108,183],"information":[111],"as":[112],"additional":[113],"spatiotemporal":[114,157],"context.":[115],"Extensive":[116],"experiments":[117],"show":[122],"that,":[123],"first,":[124],"model":[128],"can":[129,160],"not":[130],"only":[131],"produce":[132],"Chinese":[136],"descriptions":[137],"efficiently,":[142],"but":[143],"offer":[145],"improved":[146],"performance":[147],"monolingual":[150],"models.":[151],"Furthermore,":[152],"we":[153,178],"demonstrate":[154],"that":[155],"context":[159],"be":[161],"effectively":[162],"utilized":[163],"align":[165],"thus":[171],"assist":[172],"machine":[173],"translation.":[174],"In":[175],"end,":[177],"discuss":[179],"potentials":[181],"VATEXfor":[184],"other":[185],"research.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":73},{"year":2024,"cited_by_count":103},{"year":2023,"cited_by_count":88},{"year":2022,"cited_by_count":65},{"year":2021,"cited_by_count":64},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}