{"id":"https://openalex.org/W4416251305","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227846","title":"TextMamba: Scene Text Detector with Mamba","display_name":"TextMamba: Scene Text Detector with Mamba","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251305","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227846"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.06657","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109779844","display_name":"Qiyan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyan Zhao","raw_affiliation_strings":["Xiamen University of Technology,Fujian Key Laboratory of Pattern Recognition and Image Understanding,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology,Fujian Key Laboratory of Pattern Recognition and Image Understanding,Xiamen,China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101513255","display_name":"Yue Yan","orcid":"https://orcid.org/0000-0001-7657-4789"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yue Yan","raw_affiliation_strings":["The University of Sheffield,Department of Automatic Control and Systems Engineering,Sheffield,England"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Department of Automatic Control and Systems Engineering,Sheffield,England","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101620627","display_name":"Da-Han Wang","orcid":"https://orcid.org/0000-0002-0790-9028"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da-Han Wang","raw_affiliation_strings":["Xiamen University of Technology,Fujian Key Laboratory of Pattern Recognition and Image Understanding,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology,Fujian Key Laboratory of Pattern Recognition and Image Understanding,Xiamen,China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9016000032424927,"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":0.9016000032424927,"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/T10028","display_name":"Topic Modeling","score":0.04320000112056732,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.006899999920278788,"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/encoder","display_name":"Encoder","score":0.47690001130104065},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4708999991416931},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43689998984336853},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42149999737739563},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4115999937057495},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.38370001316070557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38199999928474426},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.37459999322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511999726295471},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32100000977516174},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2780882242","wikidata":"https://www.wikidata.org/wiki/Q14235582","display_name":"Literal (mathematical logic)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.06657","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.06657","pdf_url":"https://arxiv.org/pdf/2512.06657","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.06657","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.06657","pdf_url":"https://arxiv.org/pdf/2512.06657","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2601564443","https://openalex.org/W2605982830","https://openalex.org/W2785383245","https://openalex.org/W2810028092","https://openalex.org/W2914492226","https://openalex.org/W2963299604","https://openalex.org/W2967615747","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3003921261","https://openalex.org/W3034792612","https://openalex.org/W3040932449","https://openalex.org/W3085139254","https://openalex.org/W3096609285","https://openalex.org/W3159307593","https://openalex.org/W3176892444","https://openalex.org/W3186564193","https://openalex.org/W3189348500","https://openalex.org/W3196976036","https://openalex.org/W4214922754","https://openalex.org/W4312230431","https://openalex.org/W4312593844","https://openalex.org/W4372263563","https://openalex.org/W4382464147","https://openalex.org/W4385488928","https://openalex.org/W4386065412","https://openalex.org/W4386075667","https://openalex.org/W4391953425","https://openalex.org/W4392903971","https://openalex.org/W4393149654","https://openalex.org/W4399618753","https://openalex.org/W4402352424","https://openalex.org/W4402716160","https://openalex.org/W4402952320","https://openalex.org/W4403136854","https://openalex.org/W4403791273","https://openalex.org/W4405950485","https://openalex.org/W4406110380","https://openalex.org/W4409261976","https://openalex.org/W4414243662","https://openalex.org/W4415795314"],"related_works":[],"abstract_inverted_index":{"In":[0],"scene":[1,78],"text":[2,52,79],"detection,":[3],"Transformer-based":[4],"methods":[5],"have":[6],"addressed":[7],"the":[8,86,93,105,115],"global":[9],"feature":[10,144],"extraction":[11],"limitations":[12,35],"inherent":[13,37],"in":[14,120],"traditional":[15],"convolution":[16],"neural":[17],"network-based":[18],"methods.":[19],"However,":[20],"most":[21],"directly":[22],"rely":[23],"on":[24,44,82,153,163],"native":[25],"Transformer":[26],"attention":[27,90],"layers":[28],"as":[29],"encoders":[30],"without":[31],"evaluating":[32],"their":[33],"cross-domain":[34],"and":[36,113,130,142,161,166],"shortcomings:":[38],"forgetting":[39],"important":[40],"information":[41,99,112,119],"or":[42,150],"focusing":[43],"irrelevant":[45,118],"representations":[46],"when":[47],"modeling":[48,66],"long-range":[49,64],"dependencies":[50,65],"for":[51],"detection.":[53],"The":[54],"recently":[55],"proposed":[56],"state":[57,140],"space":[58],"model":[59],"Mamba":[60,83,121],"has":[61],"demonstrated":[62],"better":[63],"through":[67],"a":[68,76,126],"linear":[69],"complexity":[70],"selection":[71,87],"mechanism.":[72],"Therefore,":[73],"we":[74,124],"propose":[75],"novel":[77],"detector":[80],"based":[81],"that":[84],"integrates":[85],"mechanism":[88],"with":[89,156],"layers,":[91],"enhancing":[92],"encoder\u2019s":[94],"ability":[95],"to":[96,108,136],"extract":[97],"relevant":[98],"from":[100],"long":[101],"sequences.":[102],"We":[103],"adopt":[104],"Top_k":[106],"algorithm":[107],"explicitly":[109],"select":[110],"key":[111],"reduce":[114],"interference":[116],"of":[117,158],"modeling.":[122],"Additionally,":[123],"design":[125],"dual-scale":[127],"feed-forward":[128],"network":[129],"an":[131],"embedding":[132],"pyramid":[133],"enhancement":[134],"module":[135],"facilitate":[137],"high-dimensional":[138],"hidden":[139],"interactions":[141],"multi-scale":[143],"fusion.":[145],"Our":[146],"method":[147],"achieves":[148],"state-of-the-art":[149],"competitive":[151],"performance":[152],"various":[154],"benchmarks,":[155],"F-measures":[157],"89.7%,":[159],"89.2%,":[160],"78.5%":[162],"CTW1500,":[164],"TotalText,":[165],"ICDAR19ArT,":[167],"respectively.":[168],"Codes":[169],"will":[170],"be":[171],"available.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}