{"id":"https://openalex.org/W4411382599","doi":"https://doi.org/10.1007/s40747-025-01987-6","title":"GDText-VM: an arbitrary-shaped scene text detector based on globally deformable VMamba","display_name":"GDText-VM: an arbitrary-shaped scene text detector based on globally deformable VMamba","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411382599","doi":"https://doi.org/10.1007/s40747-025-01987-6"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-01987-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01987-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01987-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01987-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047903393","display_name":"Yingnan Zhao","orcid":"https://orcid.org/0009-0008-1706-7929"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingnan Zhao","raw_affiliation_strings":["School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100884516","display_name":"Hu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Hu","raw_affiliation_strings":["School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fangqi Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangqi Ding","raw_affiliation_strings":["School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Science, Nanjing University of Information Science and Technology, Nanjing, 210044, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009585171","display_name":"Jielin Jiang","orcid":"https://orcid.org/0000-0002-7191-8674"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielin Jiang","raw_affiliation_strings":["School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007818509","display_name":"Xiaolong Xu","orcid":"https://orcid.org/0000-0003-4879-9803"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Xu","raw_affiliation_strings":["School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Nanjing University of Information Science and Technology, Nanjing, 210044, China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047903393"],"corresponding_institution_ids":["https://openalex.org/I200845125"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11378191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"8","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":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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/computational-intelligence","display_name":"Computational intelligence","score":0.772454559803009},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5855462551116943},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5200988054275513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5110198259353638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49540913105010986},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3751402497291565},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32579493522644043},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.21923333406448364}],"concepts":[{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.772454559803009},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5855462551116943},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5200988054275513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110198259353638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49540913105010986},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3751402497291565},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32579493522644043},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.21923333406448364}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-01987-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01987-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01987-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cbd7a84cb82e4b9dbae3aa2f2dd17901","is_oa":true,"landing_page_url":"https://doaj.org/article/cbd7a84cb82e4b9dbae3aa2f2dd17901","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 8, Pp 1-19 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-01987-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01987-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01987-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2266259690","display_name":null,"funder_award_id":"62372242","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411382599.pdf","grobid_xml":"https://content.openalex.org/works/W4411382599.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2017278151","https://openalex.org/W2027883219","https://openalex.org/W2128854450","https://openalex.org/W2144554289","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2605982830","https://openalex.org/W2752782242","https://openalex.org/W2810028092","https://openalex.org/W2884585870","https://openalex.org/W2914492226","https://openalex.org/W2962721361","https://openalex.org/W2962810613","https://openalex.org/W2963125010","https://openalex.org/W2963299604","https://openalex.org/W2963516811","https://openalex.org/W2963647456","https://openalex.org/W2963840241","https://openalex.org/W2964231884","https://openalex.org/W2964294787","https://openalex.org/W2964685115","https://openalex.org/W2966926453","https://openalex.org/W2981408784","https://openalex.org/W3034552520","https://openalex.org/W3034792612","https://openalex.org/W3082397598","https://openalex.org/W3093046205","https://openalex.org/W3106250896","https://openalex.org/W3134523352","https://openalex.org/W3138516171","https://openalex.org/W3158904718","https://openalex.org/W3181016597","https://openalex.org/W3197860412","https://openalex.org/W4225262244","https://openalex.org/W4291910337","https://openalex.org/W4324119109","https://openalex.org/W4384023659","https://openalex.org/W4385292311","https://openalex.org/W4386172471","https://openalex.org/W4391769232","https://openalex.org/W4399495323","https://openalex.org/W4402774414","https://openalex.org/W4402952320","https://openalex.org/W6600424091","https://openalex.org/W6630516856"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Detecting":[0],"arbitrary-shaped":[1],"text":[2,15,72,150,190,209],"in":[3,10,24,59,152,221],"natural":[4],"scenes":[5],"remains":[6],"a":[7,40,69,88,108],"significant":[8],"challenge":[9],"deep":[11],"learning":[12],"research.":[13],"Contemporary":[14],"detectors":[16],"based":[17],"on":[18,131,137,184,198,245,248,252],"Convolutional":[19],"Neural":[20],"Networks":[21],"face":[22],"challenges":[23],"effectively":[25,177],"modeling":[26,36],"long-range":[27,47,105],"dependencies.":[28],"While":[29],"Vision":[30],"Transformers":[31],"theoretically":[32],"enable":[33],"global":[34,89,109,172],"context":[35],"via":[37],"self-attention":[38],"mechanisms,":[39],"computational":[41,57,118],"framework":[42],"designed":[43],"for":[44],"establishing":[45],"effective":[46],"dependency":[48],"modeling,":[49],"their":[50],"practical":[51],"implementation":[52],"is":[53],"constrained":[54],"by":[55],"quadratic":[56],"complexity":[58],"real-world":[60],"scenarios.":[61],"To":[62],"address":[63],"these":[64],"challenges,":[65],"this":[66,156],"study":[67,157,194],"proposes":[68],"novel":[70],"scene":[71,208],"detector":[73,86],"called":[74],"GDText-VM":[75,124,147,205,216,239],"(Globally":[76],"Deformable":[77],"Text-VMamba),":[78],"developed":[79],"using":[80],"the":[81,101,121,144,153,169,179,218],"deformable":[82,126],"VMamba":[83],"framework.":[84],"This":[85,98,166,193],"incorporates":[87],"channel-spatial":[90],"attention":[91],"mechanism":[92],"along":[93],"with":[94,206,232],"Fourier":[95,154],"contour":[96],"modeling.":[97],"approach":[99],"enhances":[100],"capability":[102,145],"to":[103,128,142,148,203],"capture":[104],"dependencies,":[106],"achieving":[107],"receptive":[110],"field":[111],"and":[112,134,174,187,201,226,235,250],"rapid":[113],"convergence":[114],"while":[115,228],"maintaining":[116,229],"linear":[117],"complexity.":[119],"Unlike":[120],"original":[122],"VMamba,":[123],"integrates":[125],"convolutions":[127],"enhance":[129],"focus":[130],"local":[132],"regions":[133],"reduces":[135],"reliance":[136],"cross-shaped":[138],"activation":[139],"patterns.":[140],"Additionally,":[141],"improve":[143],"of":[146,171,181,223,243],"fit":[149],"contours":[151],"domain,":[155],"introduces":[158],"an":[159],"innovative":[160],"Global":[161],"Attention":[162],"Shuffle":[163],"Module":[164],"(GASM).":[165],"module":[167],"facilitates":[168],"fusion":[170],"channel":[173],"spatial":[175],"features,":[176],"mitigating":[178],"impact":[180],"feature":[182],"imbalance":[183],"fitting":[185],"performance":[186],"significantly":[188],"enhancing":[189],"detection":[191,210],"accuracy.":[192],"conducts":[195],"comprehensive":[196],"experiments":[197],"Total-Text,":[199,246],"CTW1500,":[200,249],"ICDAR2015":[202],"compare":[204],"classical":[207],"approaches.":[211],"The":[212],"results":[213],"indicate":[214],"that":[215],"outperforms":[217],"state-of-the-art":[219],"methods":[220],"terms":[222],"precision,":[224],"recall,":[225],"F-measure,":[227],"efficient":[230],"computation":[231],"25.88M":[233],"parameters":[234],"40.83G":[236],"FLOPs.":[237],"Notably,":[238],"achieves":[240],"F-measure":[241],"values":[242],"88.5%":[244],"88.9%":[247],"88.6%":[251],"ICDAR2015.":[253]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}