{"id":"https://openalex.org/W4200633461","doi":"https://doi.org/10.48550/arxiv.2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","display_name":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4200633461","doi":"https://doi.org/10.48550/arxiv.2112.04888"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2112.04888","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.04888","pdf_url":"https://arxiv.org/pdf/2112.04888","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.04888","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101634167","display_name":"Weijia Wu","orcid":"https://orcid.org/0000-0003-3912-7212","observed_orcids":["https://orcid.org/0000-0003-3912-7212","https://orcid.org/0009-0007-2957-957X"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Weijia","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760616","display_name":"Yuanqiang Cai","orcid":"https://orcid.org/0000-0001-8041-012X","observed_orcids":["https://orcid.org/0000-0001-8041-012X"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai, Yuanqiang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103145743","display_name":"Debing Zhang","orcid":"https://orcid.org/0000-0003-4048-0531","observed_orcids":["https://orcid.org/0000-0003-4048-0531"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Debing","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Sibo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Sibo","raw_affiliation_strings":["Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393942","display_name":"Zhuang Li","orcid":"https://orcid.org/0000-0002-4211-6525","observed_orcids":["https://orcid.org/0000-0002-4211-6525","https://orcid.org/0009-0009-1713-7402","https://orcid.org/0009-0006-8346-5488"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhuang","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658802","display_name":"Jiahong Li","orcid":"https://orcid.org/0009-0003-6844-808X","observed_orcids":["https://orcid.org/0009-0003-6844-808X"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Jiahong","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011779639","display_name":"Yejun Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Yejun","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhou, Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Hong","raw_affiliation_strings":["Kuaishou Technology , Beijing , China","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9955999851226807,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9955999851226807,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0012000000569969416,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.4000000059604645},{"id":"https://openalex.org/keywords/scene-text","display_name":"scene text","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8603111505508423},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7843388319015503},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6281523704528809},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5352573990821838},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5010895729064941},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4922250807285309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48331689834594727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45547154545783997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4300451874732971},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42690154910087585},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3518756926059723},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2112.04888","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.04888","pdf_url":"https://arxiv.org/pdf/2112.04888","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2112.04888","doi":"https://doi.org/10.48550/arxiv.2112.04888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2112.04888","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.04888","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.04888","pdf_url":"https://arxiv.org/pdf/2112.04888","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200633461.pdf","grobid_xml":"https://content.openalex.org/works/W4200633461.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402216502","https://openalex.org/W4400584620","https://openalex.org/W4390723627","https://openalex.org/W4385768155","https://openalex.org/W4399198630","https://openalex.org/W4286229584","https://openalex.org/W3106963860","https://openalex.org/W4416048047","https://openalex.org/W4415798460","https://openalex.org/W4389705007"],"abstract_inverted_index":{"Most":[0],"existing":[1,52],"video":[2,119,134],"text":[3,28,57,82,105,120,131,169],"spotting":[4,121,132],"benchmarks":[5],"focus":[6],"on":[7],"evaluating":[8],"a":[9,22,68,136,152,161],"single":[10],"language":[11],"and":[12,112,159,185,194],"scenario":[13],"with":[14,42,55,67,123,135,178],"limited":[15],"data.":[16],"In":[17],"this":[18],"work,":[19],"we":[20,38,115],"introduce":[21],"large-scale,":[23],"Bilingual,":[24],"Open":[25],"World":[26],"Video":[27],"benchmark":[29],"dataset(BOVText).":[30],"There":[31],"are":[32,91],"four":[33],"features":[34,146],"for":[35,93,155],"BOVText.":[36],"Firstly,":[37],"provide":[39],"2,000+":[40],"videos":[41],"more":[43],"than":[44,50],"1,750,000+":[45],"frames,":[46],"25":[47],"times":[48],"larger":[49],"the":[51,94,101,129,148,156,167,175],"largest":[53],"dataset":[54,62,184],"incidental":[56],"in":[58,98,133],"videos.":[59],"Secondly,":[60],"our":[61],"covers":[63],"30+":[64],"open":[65],"categories":[66],"wide":[69],"selection":[70],"of":[71,187],"various":[72],"scenarios,":[73],"e.g.,":[74],"Life":[75],"Vlog,":[76],"Driving,":[77],"Movie,":[78],"etc.":[79],"Thirdly,":[80],"abundant":[81],"types":[83],"annotation":[84,106],"(i.e.,":[85],"title,":[86],"caption":[87],"or":[88],"scene":[89],"text)":[90],"provided":[92],"different":[95],"representational":[96],"meanings":[97],"video.":[99],"Fourthly,":[100],"BOVText":[102],"provides":[103],"bilingual":[104],"to":[107,165],"promote":[108],"multiple":[109],"cultures":[110],"live":[111],"communication.":[113],"Besides,":[114],"propose":[116],"an":[117],"end-to-end":[118],"framework":[122],"Transformer,":[124],"termed":[125],"TransVTSpotter,":[126],"which":[127],"solves":[128],"multi-orient":[130],"simple,":[137],"but":[138],"efficient":[139],"attention-based":[140],"query-key":[141],"mechanism.":[142],"It":[143],"applies":[144],"object":[145],"from":[147],"previous":[149],"frame":[150,158],"as":[151],"tracking":[153],"query":[154],"current":[157],"introduces":[160],"rotation":[162],"angle":[163],"prediction":[164],"fit":[166],"multiorient":[168],"instance.":[170],"On":[171],"ICDAR2015(video),":[172],"TransVTSpotter":[173,188],"achieves":[174],"state-of-the-art":[176],"performance":[177],"44.1%":[179],"MOTA,":[180],"9":[181],"fps.":[182],"The":[183],"code":[186],"can":[189],"be":[190],"found":[191],"at":[192],"github:com=weijiawu=BOVText":[193],"github:com=weijiawu=TransVTSpotter,":[195],"respectively.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2021-12-31T00:00:00"}
