{"id":"https://openalex.org/W7164513580","doi":"https://doi.org/10.3390/info17060585","title":"ASM-DBNet: Introducing Adaptive Differentiable Binarization, Spatial-Channel Self-Attention and Multi-Scale Context-Enhanced Dynamic Upsampling for Natural Scene Text Detection","display_name":"ASM-DBNet: Introducing Adaptive Differentiable Binarization, Spatial-Channel Self-Attention and Multi-Scale Context-Enhanced Dynamic Upsampling for Natural Scene Text Detection","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164513580","doi":"https://doi.org/10.3390/info17060585"},"language":"en","primary_location":{"id":"doi:10.3390/info17060585","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17060585","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/info17060585","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000359310","display_name":"Xiaoliang Qian","orcid":"https://orcid.org/0000-0002-4328-6411"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang Qian","raw_affiliation_strings":["College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":"https://orcid.org/0000-0002-4328-6411","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138550527","display_name":"Pengfei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wang","raw_affiliation_strings":["College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138545459","display_name":"Li Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zeng","raw_affiliation_strings":["College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084150182","display_name":"Mengyang Chen","orcid":"https://orcid.org/0000-0002-2813-8429"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyang Chen","raw_affiliation_strings":["College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138521851","display_name":"Wandian Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wandian Chen","raw_affiliation_strings":["College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111615028","display_name":"Jinchao Guo","orcid":"https://orcid.org/0000-0001-5561-3419"},"institutions":[{"id":"https://openalex.org/I23171815","display_name":"Zhengzhou University of Light Industry","ror":"https://ror.org/05fwr8z16","country_code":"CN","type":"education","lineage":["https://openalex.org/I23171815"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinchao Guo","raw_affiliation_strings":["College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China","institution_ids":["https://openalex.org/I23171815"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138548896","display_name":"Yanfang Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117020","display_name":"Nantong Science and Technology Bureau","ror":"https://ror.org/02tx34m84","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210117020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfang Mao","raw_affiliation_strings":["State Grid Nantong Power Supply Company, Nantong 226000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Nantong Power Supply Company, Nantong 226000, China","institution_ids":["https://openalex.org/I4210117020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7349984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"6","first_page":"585","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9372000098228455,"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":0.9372000098228455,"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":0.020400000736117363,"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":0.0038999998942017555,"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/upsampling","display_name":"Upsampling","score":0.784500002861023},{"id":"https://openalex.org/keywords/deconvolution","display_name":"Deconvolution","score":0.5386000275611877},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.534600019454956},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47620001435279846},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.47540000081062317},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4530999958515167},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.3898000121116638},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.38100001215934753},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3531000018119812}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.784500002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6913999915122986},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4853000044822693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C17828673","wikidata":"https://www.wikidata.org/wiki/Q7334899","display_name":"Ringing artifacts","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info17060585","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17060585","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d954c8db05464aad918d7f34f79ebd49","is_oa":false,"landing_page_url":"https://doaj.org/article/d954c8db05464aad918d7f34f79ebd49","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 17, Iss 6, p 585 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info17060585","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17060585","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2298392526","display_name":null,"funder_award_id":"252300421063","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G2663363119","display_name":null,"funder_award_id":"24ZX005","funder_id":"https://openalex.org/F4320325625","funder_display_name":"Education Department of Henan Province"},{"id":"https://openalex.org/G2850872778","display_name":null,"funder_award_id":"62076223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null},{"id":"https://openalex.org/F4320325625","display_name":"Education Department of Henan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1745334888","https://openalex.org/W1988461287","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2412782625","https://openalex.org/W2531409750","https://openalex.org/W2810028092","https://openalex.org/W2953606406","https://openalex.org/W2963647456","https://openalex.org/W2964685115","https://openalex.org/W2987322772","https://openalex.org/W2991626090","https://openalex.org/W3172799005","https://openalex.org/W3179426054","https://openalex.org/W4200020806","https://openalex.org/W4214922754","https://openalex.org/W4221097663","https://openalex.org/W4293679656","https://openalex.org/W4308220235","https://openalex.org/W4375928714","https://openalex.org/W4376456529","https://openalex.org/W4383113591","https://openalex.org/W4385988828","https://openalex.org/W4386180224","https://openalex.org/W4396778191","https://openalex.org/W4396977651","https://openalex.org/W4399495323","https://openalex.org/W4403722763","https://openalex.org/W4405778871","https://openalex.org/W4406457758","https://openalex.org/W4407736541","https://openalex.org/W4408791786","https://openalex.org/W7082976631"],"related_works":[],"abstract_inverted_index":{"Text":[0],"detection":[1,41,86],"models":[2,17],"based":[3,180,246],"on":[4,174,181,247,289],"DBNet":[5],"have":[6],"demonstrated":[7],"strong":[8],"performance":[9,133],"in":[10,30,68,215,223],"natural":[11],"scene":[12],"text":[13,40,74,85],"detection.":[14],"However,":[15],"these":[16,248],"still":[18],"suffer":[19],"from":[20],"the":[21,26,31,39,48,56,65,69,78,97,123,130,135,138,150,158,167,175,189,198,212,216,224,252,261,264,290,306],"following":[22],"three":[23,94],"issues.":[24],"Firstly,":[25],"amplifying":[27,112,125],"factor":[28,113,126],"hyperparameter":[29],"differentiable":[32,102],"binarization":[33,103],"(DB)":[34],"makes":[35],"it":[36],"difficult":[37],"for":[38,114],"model":[42,87],"to":[43,148,165,187,210],"achieve":[44],"optimal":[45],"performance.":[46],"Secondly,":[47],"integration":[49],"of":[50,93,134,152,171,192,226,240,263,284,300],"low-level":[51,155,195],"and":[52,121,154,194,234,271,287,294,303],"high-level":[53,153,172,193],"features":[54],"within":[55],"backbone\u2019s":[57],"feature":[58,115,232],"pyramid":[59],"lacks":[60],"specific":[61],"optimization":[62,132],"strategies.":[63],"Thirdly,":[64],"deconvolution":[66,213],"operation":[67,214],"prediction":[70,217],"head":[71],"may":[72],"damage":[73],"contours.":[75],"To":[76],"tackle":[77],"aforementioned":[79],"issues,":[80],"this":[81],"paper":[82],"presents":[83],"a":[84,141,182,201],"termed":[88],"ASM-DBNet,":[89],"which":[90],"mainly":[91],"consists":[92],"innovations.":[95],"For":[96,137,197],"first":[98],"issue,":[99,140,200],"an":[100],"adaptive":[101],"(ADB)":[104],"scheme":[105],"is":[106,146,163,185,208],"proposed.":[107],"It":[108,219],"can":[109],"independently":[110],"predict":[111],"points":[116,228],"at":[117],"different":[118],"spatial":[119,161,168,253],"locations":[120],"replace":[122,211],"original":[124],"hyperparameter,":[127],"thereby":[128],"improving":[129],"overall":[131],"model.":[136,308],"second":[139],"spatial-channel":[142],"self-attention":[143,162,179],"(SCA)":[144],"module":[145,207],"proposed":[147,209],"optimize":[149,188],"fusion":[151,190],"features.":[156,196],"On":[157],"one":[159],"hand,":[160,177],"used":[164,186],"enhance":[166],"localization":[169],"ability":[170],"features;":[173],"other":[176],"channel":[178],"grouped":[183],"transformer":[184],"results":[191],"third":[199],"multi-scale":[202,230],"context-enhanced":[203],"dynamic":[204],"upsampling":[205],"(MC-DyUpS)":[206],"head.":[218],"enhances":[220],"contextual":[221],"perception":[222],"region":[225],"interpolation":[227,241],"through":[229],"context":[231],"extraction,":[233],"then":[235],"accurately":[236],"predicts":[237],"coordinate":[238],"offsets":[239,249],"points.":[242],"The":[243],"position":[244],"correction":[245],"effectively":[250],"suppresses":[251],"deviation":[254],"caused":[255],"by":[256],"deconvolution.":[257],"Ablation":[258],"studies":[259],"demonstrate":[260,278],"effectiveness":[262],"SCA":[265],"module,":[266,268],"MC-DyUpS":[267],"ADB":[269],"scheme,":[270],"their":[272],"arbitrary":[273],"combinations.":[274],"Comprehensive":[275],"quantitative":[276],"evaluations":[277],"that":[279],"ASM-DBNet":[280],"achieves":[281],"competitive":[282],"F1-scores":[283],"84.1%,":[285],"84.2%,":[286],"85.7%":[288],"ICDAR":[291],"2015,":[292],"Total-Text,":[293],"MSRA-TD500":[295],"datasets,":[296],"respectively,":[297],"with":[298],"improvements":[299],"1.8%,":[301],"1.4%,":[302],"2.9%":[304],"over":[305],"baseline":[307]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-13T00:00:00"}