{"id":"https://openalex.org/W7131867678","doi":"https://doi.org/10.1109/tmm.2026.3668498","title":"TextDCTv2: Scene Text Detection With Patch-Based Discrete Cosine Transform Representation","display_name":"TextDCTv2: Scene Text Detection With Patch-Based Discrete Cosine Transform Representation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131867678","doi":"https://doi.org/10.1109/tmm.2026.3668498"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668498","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127188990","display_name":"Zhaolong Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaolong Pan","raw_affiliation_strings":["College of Computer Science and Artifical Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-1457-5940","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artifical Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127160911","display_name":"Yuchen Su","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Su","raw_affiliation_strings":["College of Computer Science and Artifical Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7743-8260","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artifical Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127392834","display_name":"Lina Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I49934816","display_name":"Hunan University of Technology","ror":"https://ror.org/04j3vr751","country_code":"CN","type":"education","lineage":["https://openalex.org/I49934816"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Tan","raw_affiliation_strings":["School of Computer Science, Hunan University of Technology and Business, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hunan University of Technology and Business, Changsha, China","institution_ids":["https://openalex.org/I49934816"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Gao","orcid":"https://orcid.org/0000-0002-5176-628X"},"institutions":[{"id":"https://openalex.org/I2801045807","display_name":"Shenzhen Stock Exchange","ror":"https://ror.org/058h0n244","country_code":"CN","type":"other","lineage":["https://openalex.org/I2801045807"]},{"id":"https://openalex.org/I4210097777","display_name":"China General Nuclear Power Corporation (China)","ror":"https://ror.org/00fpj7t66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210097777"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Shenzhen Power Supply Company, Ltd., Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-5176-628X","affiliations":[{"raw_affiliation_string":"Shenzhen Power Supply Company, Ltd., Guangdong, China","institution_ids":["https://openalex.org/I2801045807","https://openalex.org/I4210097777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127101019","display_name":"Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2801045807","display_name":"Shenzhen Stock Exchange","ror":"https://ror.org/058h0n244","country_code":"CN","type":"other","lineage":["https://openalex.org/I2801045807"]},{"id":"https://openalex.org/I4210097777","display_name":"China General Nuclear Power Corporation (China)","ror":"https://ror.org/00fpj7t66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210097777"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Shenzhen Power Supply Company, Ltd., Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Power Supply Company, Ltd., Guangdong, China","institution_ids":["https://openalex.org/I2801045807","https://openalex.org/I4210097777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121918718","display_name":"Zhineng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1543-6889","affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210139618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24435719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5849","last_page":"5862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.796999990940094,"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":0.796999990940094,"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":0.04230000078678131,"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":0.03579999879002571,"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/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.754800021648407},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5792999863624573},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5468000173568726},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.4553999900817871},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.36649999022483826},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3598000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.754800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284000277519226},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5468000173568726},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4636000096797943},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.30660000443458557},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668498","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6146631126","display_name":null,"funder_award_id":"62172103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7791778128","display_name":null,"funder_award_id":"32341012","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Regression-based":[0],"scene":[1,88],"text":[2,8,89,104,119,223,234],"detection":[3,90],"methods,":[4],"which":[5,36,94],"mainly":[6],"locate":[7],"by":[9],"regressing":[10],"parameterized":[11,18,48,70],"curves,":[12],"have":[13],"become":[14],"popular":[15],"recently.":[16],"However,":[17,72],"curves":[19,31],"typically":[20],"require":[21],"a":[22,52,86,108,163,172,202,210],"pre-defined":[23],"starting":[24],"coordinate":[25],"and":[26,61,129,148,180,220,232,270],"direction":[27],"for":[28,205],"the":[29,47,69,96,117,124,189,193,198,267,279],"contour":[30,66],"to":[32,101,116,139,146,176,214,245],"ensure":[33],"consistent":[34],"learning,":[35],"limits":[37],"their":[38,217],"flexibility":[39],"in":[40],"representing":[41,68],"arbitrary-shaped":[42],"text.":[43],"Methods":[44],"based":[45,183],"on":[46,132,141,184,250,266,278],"mask":[49,57,106,125,235],"would":[50],"be":[51],"promising":[53],"alternative.":[54],"Text":[55],"instance":[56,105,120],"naturally":[58],"has":[59],"consistency":[60],"is":[62,159,243],"less":[63,79],"noisy":[64],"than":[65],"vertices":[67],"curves.":[71],"this":[73,82],"branch":[74],"of":[75,112,192,201,247,258,273],"methods":[76,249],"still":[77],"remains":[78],"studied.":[80],"In":[81],"work,":[83],"we":[84,122,170,208,228],"propose":[85],"novel":[87],"framework,":[91],"named":[92],"TextDCTv2,":[93],"adopts":[95],"discrete":[97],"cosine":[98],"transform":[99],"(DCT)":[100],"represent":[102],"each":[103,133,157],"as":[107],"compact":[109],"vector.":[110],"Instead":[111],"simply":[113],"applying":[114],"DCT":[115,131,194,218],"entire":[118],"mask,":[121],"split":[123],"into":[126,162],"multiple":[127],"patches":[128,182],"perform":[130],"patch":[134,158],"individually.":[135],"This":[136],"allows":[137],"us":[138],"focus":[140],"regions":[142],"that":[143,196,240],"are":[144],"difficult":[145],"detect":[147,177],"then":[149],"refine":[150],"them":[151],"without":[152],"affecting":[153],"other":[154],"patches.":[155],"Specifically,":[156,253],"first":[160],"transformed":[161],"frequency":[164],"domain":[165],"matrix":[166,195],"using":[167],"DCT.":[168],"Then,":[169],"introduce":[171],"direct":[173,185],"current":[174,186],"identifier":[175],"foreground,":[178],"background":[179],"challenging":[181,206],"coefficients,":[187],"i.e.,":[188],"zero-frequency":[190],"components":[191],"reflect":[197],"overall":[199],"brightness":[200],"patch.":[203],"Next,":[204],"patches,":[207],"employ":[209],"lightweight":[211],"refinement":[212],"regressor":[213],"further":[215],"correct":[216],"vectors":[219],"generate":[221],"precise":[222,233],"boundaries.":[224],"Through":[225],"these":[226],"designs,":[227],"achieve":[229],"an":[230,256,271],"efficient":[231],"representation.":[236],"Extensive":[237],"experiments":[238],"prove":[239],"our":[241],"method":[242],"superior":[244],"most":[246],"existing":[248],"various":[251],"datasets.":[252],"TextDCTv2":[254],"achieves":[255],"F-measure":[257],"88.7":[259],"at":[260,275],"20.3":[261],"frames":[262],"per":[263],"second":[264],"(FPS)":[265],"Total-Text":[268],"dataset,":[269],"Fmeasure":[272],"87.8":[274],"30.3":[276],"FPS":[277],"CTW1500":[280],"dataset.":[281]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-28T00:00:00"}