{"id":"https://openalex.org/W7082663133","doi":"https://doi.org/10.3724/2096-7004.di.2025.0127","title":"Modifying SwinTextSpotter for Vietnamese Scene Text Spotting","display_name":"Modifying SwinTextSpotter for Vietnamese Scene Text Spotting","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W7082663133","doi":"https://doi.org/10.3724/2096-7004.di.2025.0127"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0127","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0127","pdf_url":"https://www.sciengine.com/doi/pdf/4A8B1CD0C1C64CB6AE99716E00C1098B","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/4A8B1CD0C1C64CB6AE99716E00C1098B","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yimin Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yimin Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wenhui Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhui Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruiqi Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiqi Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liyu Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liyu Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lianxi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianxi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Vinh Loc Cu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinh Loc Cu","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":1.396,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88653223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"8","issue":"1","first_page":"244","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6468999981880188,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6468999981880188,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.024399999529123306,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7339000105857849},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7146999835968018},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5974000096321106},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5170999765396118},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.39259999990463257},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.34689998626708984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3456999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802000045776367},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7339000105857849},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7146999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7064999938011169},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5911999940872192},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5170999765396118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40689998865127563},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.34689998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0127","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0127","pdf_url":"https://www.sciengine.com/doi/pdf/4A8B1CD0C1C64CB6AE99716E00C1098B","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0127","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0127","pdf_url":"https://www.sciengine.com/doi/pdf/4A8B1CD0C1C64CB6AE99716E00C1098B","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.42899322509765625,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7082663133.pdf","grobid_xml":"https://content.openalex.org/works/W7082663133.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"scene":[1,143],"text":[2,22,44,144],"spotting,":[3],"which":[4],"jointly":[5],"localizes":[6],"and":[7,18,32,96],"recognizes":[8],"texts":[9],"in":[10],"natural":[11],"images,":[12],"has":[13],"advanced":[14],"significantly":[15],"for":[16,99],"Chinese":[17],"English.":[19],"However,":[20],"Vietnamese":[21,43,71,142],"spotting":[23,45],"remains":[24],"challenging":[25],"due":[26],"to":[27,59,66,84,115],"frequent":[28],"diacritic":[29,123],"recognition":[30,106,135],"failures":[31],"missed":[33],"detections.":[34],"To":[35],"bridge":[36],"this":[37],"gap,":[38],"we":[39,52,77,108],"proposed":[40,53,78],"a":[41],"diacritic-focused":[42],"framework":[46,133],"that":[47,131],"mitigates":[48],"background":[49],"interference.":[50],"Specifically,":[51],"the":[54,67,74,79,86,91,105,110,117],"Dilated":[55],"Deformable":[56],"Convolution":[57],"Module":[58,83,114],"capture":[60,116],"fine-grained":[61],"diacritical":[62],"features":[63],"by":[64],"adapting":[65],"structural":[68],"characteristics":[69],"of":[70,102],"character.":[72],"During":[73,104],"detection":[75],"phase,":[76,107],"Global":[80],"Feature":[81],"Fusion":[82],"help":[85],"model":[87],"more":[88],"accurately":[89],"understand":[90],"relationship":[92],"between":[93],"local":[94],"details":[95],"global":[97],"context":[98],"each":[100],"region":[101],"interest.":[103],"designed":[109],"Cross":[111],"Channel":[112],"Attention":[113],"spatial":[118],"relationships":[119],"while":[120],"discriminating":[121],"subtle":[122],"variations":[124],"through":[125],"channel-wise":[126],"recalibration.":[127],"Extensive":[128],"experiments":[129],"demonstrate":[130],"our":[132],"improves":[134],"accuracy":[136],"over":[137],"several":[138],"state-of-the-art":[139],"methods":[140],"on":[141],"benchmarks.":[145],"The":[146],"code":[147],"is":[148],"available":[149],"at":[150],"<uri":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"":[152],"xlink:href=\"https://github.com/mlmmwym/FCVintextSpotter\">https://github.com/mlmmwym/FCVintextSpotter</uri>.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2025-10-10T00:00:00"}