{"id":"https://openalex.org/W4406357813","doi":"https://doi.org/10.18293/jvlc2024-n1-061","title":"An Improved DBNet Model with Pyramid Pooling and Multi\u2010Scale Enhancement for Small Text Object Detection","display_name":"An Improved DBNet Model with Pyramid Pooling and Multi\u2010Scale Enhancement for Small Text Object Detection","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406357813","doi":"https://doi.org/10.18293/jvlc2024-n1-061"},"language":"en","primary_location":{"id":"doi:10.18293/jvlc2024-n1-061","is_oa":true,"landing_page_url":"https://doi.org/10.18293/jvlc2024-n1-061","pdf_url":"https://doi.org/10.18293/jvlc2024-n1-061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Visual Language and Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18293/jvlc2024-n1-061","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhu Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wuxuan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wuxuan Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100958217","display_name":"Yao Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454866","display_name":"Chengjun Liu","orcid":"https://orcid.org/0000-0002-2036-0770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengjun Liu","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":0.23742386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2024","issue":"1","first_page":"31","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9469000101089478,"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":0.9469000101089478,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8269065618515015},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.7372862100601196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5622161626815796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5578199028968811},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5452606678009033},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5378872752189636},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5231872200965881},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47346821427345276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3725090026855469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15278789401054382},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.13079991936683655},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10110312700271606},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07187551259994507}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8269065618515015},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7372862100601196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5622161626815796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5578199028968811},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5452606678009033},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5378872752189636},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5231872200965881},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47346821427345276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725090026855469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15278789401054382},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.13079991936683655},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10110312700271606},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07187551259994507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18293/jvlc2024-n1-061","is_oa":true,"landing_page_url":"https://doi.org/10.18293/jvlc2024-n1-061","pdf_url":"https://doi.org/10.18293/jvlc2024-n1-061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Visual Language and Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.18293/jvlc2024-n1-061","is_oa":true,"landing_page_url":"https://doi.org/10.18293/jvlc2024-n1-061","pdf_url":"https://doi.org/10.18293/jvlc2024-n1-061","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Visual Language and Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406357813.pdf","grobid_xml":"https://content.openalex.org/works/W4406357813.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Detecting":[0],"small":[1,18,50,70,124],"text":[2],"objects":[3,51],"has":[4],"been":[5],"a":[6,115],"key":[7],"focus":[8],"in":[9,26,44,194],"object":[10,46,71],"detection":[11,47],"research":[12],"due":[13],"to":[14,24,31,127,143,160,183],"their":[15],"unique":[16],"characteristics:":[17],"size,":[19],"limited":[20],"semantic":[21,129],"information,":[22,108],"susceptibility":[23],"interference":[25],"complex":[27],"scenes,":[28],"and":[29,61,97,106,140,150,152,154,162,176],"tendency":[30],"be":[32],"easily":[33,53],"obscured,":[34],"among":[35],"others.At":[36],"present,":[37],"there":[38],"are":[39,52],"still":[40],"two":[41,89,118],"common":[42],"issues":[43],"representative":[45],"models:":[48],"First,":[49],"interfered":[54],"by":[55,87,109],"the":[56,67,84,91,98,111,156,171,184,187,197],"background":[57],"or":[58],"other":[59],"objects,":[60],"second,":[62],"multi-layer":[63],"feature":[64,72,100],"networks":[65],"cause":[66],"loss":[68],"of":[69,83,114,123,131,196],"information.To":[73],"address":[74],"these":[75],"challenges,":[76],"this":[77],"paper":[78],"proposes":[79],"an":[80],"improved":[81],"version":[82],"DBNet":[85],"model":[86,189],"introducing":[88],"modules:":[90],"contextual":[92,107],"information":[93,130],"fusion":[94],"module":[95,102],"SPP-CIF":[96],"multi-scale":[99,165],"enhancement":[101],"DA-MSFE.SPP-CIF":[103],"fuses":[104],"global":[105],"replacing":[110],"pooling":[112],"layer":[113],"pyramid":[116],"with":[117],"sequentially":[119],"concatenated":[120],"dilated":[121],"convolutions":[122],"expansion":[125],"rates,":[126],"encode":[128],"high-level":[132],"features":[133,146],"at":[134,147],"multiple":[135],"scales.DA-MSFE":[136],"employs":[137],"spatial":[138],"attention":[139],"channel":[141],"self-attention":[142],"select":[144],"critical":[145],"different":[148],"scales":[149],"locations,":[151],"mines":[153],"exploits":[155],"correlations":[157],"between":[158],"channels":[159],"enhance":[161],"dynamically":[163],"aggregate":[164],"features.Extensive":[166],"experiments":[167],"were":[168],"conducted":[169],"on":[170],"publicly":[172],"available":[173],"datasets":[174],"MSRA-TD500":[175],"ICDAR2015.The":[177],"experimental":[178],"results":[179],"show":[180],"that":[181],"compared":[182],"baseline":[185],"model,":[186],"proposed":[188],"exhibits":[190],"significantly":[191],"superior":[192],"performance":[193],"terms":[195],"evaluation":[198],"metrics.":[199]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}