{"id":"https://openalex.org/W4372263563","doi":"https://doi.org/10.1109/icassp49357.2023.10096961","title":"DTTR: Detecting Text with Transformers","display_name":"DTTR: Detecting Text with Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263563","doi":"https://doi.org/10.1109/icassp49357.2023.10096961"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5100645589","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0003-4439-6118"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,Changsha,China","College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078944975","display_name":"Zhiqiang You","orcid":"https://orcid.org/0000-0001-9924-0685"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang You","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,Changsha,China","College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056160622","display_name":"Zhiwei Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Zhong","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,Changsha,China","College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346801","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0002-2329-502X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China","School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Computer Science and Technology,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109387304","display_name":"Langqi Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Langqi Mei","raw_affiliation_strings":["Ningbo Port Information Communication Co., Ltd.,Ningbo,China","Ningbo Port Information Communication Co., Ltd., Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Port Information Communication Co., Ltd.,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"Ningbo Port Information Communication Co., Ltd., Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006758918","display_name":"Shenguang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenguang Huang","raw_affiliation_strings":["Ningbo Port Information Communication Co., Ltd.,Ningbo,China","Ningbo Port Information Communication Co., Ltd., Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Ningbo Port Information Communication Co., Ltd.,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"Ningbo Port Information Communication Co., Ltd., Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100645589"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.2456,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49585802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9926000237464905,"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":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.7781597375869751},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.625730037689209},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6226621270179749},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6115403175354004},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6027902364730835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5735200047492981},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5489396452903748},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47474056482315063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42389652132987976},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3575785160064697},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1542147397994995},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12283983826637268},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10118108987808228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781597375869751},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.625730037689209},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6226621270179749},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6115403175354004},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6027902364730835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5735200047492981},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5489396452903748},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47474056482315063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42389652132987976},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3575785160064697},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1542147397994995},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12283983826637268},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10118108987808228},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":30,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2601564443","https://openalex.org/W2605076167","https://openalex.org/W2896457183","https://openalex.org/W2914492226","https://openalex.org/W2953606406","https://openalex.org/W2963299604","https://openalex.org/W2964015378","https://openalex.org/W2966926453","https://openalex.org/W2967615747","https://openalex.org/W2998621280","https://openalex.org/W3030520226","https://openalex.org/W3034514377","https://openalex.org/W3094502228","https://openalex.org/W3181016597","https://openalex.org/W3186906052","https://openalex.org/W3205961173","https://openalex.org/W3213165621","https://openalex.org/W4214922754","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6778485988","https://openalex.org/W6778883912","https://openalex.org/W6793994356","https://openalex.org/W6798837711","https://openalex.org/W6809340496"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Recently,":[0],"most":[1],"transformer-based":[2,27],"approaches":[3],"have":[4],"achieved":[5],"considerable":[6],"success":[7],"on":[8,115],"vision":[9],"tasks,":[10],"even":[11],"better":[12],"than":[13,106],"those":[14],"with":[15,32,110],"convolution":[16],"neural":[17],"networks":[18],"(CNNs).":[19],"In":[20,39,61],"this":[21],"paper,":[22],"we":[23,63],"present":[24],"a":[25,41,49,57,65,111],"novel":[26],"model,":[28],"named":[29],"detecting":[30],"text":[31,37],"transformers":[33],"(DTTR),":[34],"for":[35,88],"scene":[36,58],"detection.":[38],"DTTR,":[40],"CNN":[42],"backbone":[43,112],"extracts":[44],"local":[45],"connectivity":[46],"features":[47],"and":[48,84,100],"transformer":[50],"decoder":[51],"captures":[52],"global":[53],"context":[54],"information":[55],"from":[56],"text,":[59],"effectively.":[60],"addition,":[62],"propose":[64],"dynamic":[66],"scale":[67,82],"fusion":[68],"(DSF)":[69],"module":[70],"that":[71,94],"can":[72],"fuse":[73],"multiscale":[74],"feature":[75],"maps":[76],"dynamically,":[77],"thus":[78],"significantly":[79],"improving":[80],"the":[81,107],"robustness":[83],"rendering":[85],"powerful":[86],"representations":[87],"subsequent":[89],"decoding.":[90],"Experimental":[91],"results":[92],"show":[93],"DTTR":[95],"achieves":[96],"0.5%":[97],"H-mean":[98],"improvements":[99],"20.0%":[101],"faster":[102],"in":[103],"inference":[104],"speed":[105],"SOTA":[108],"model":[109],"of":[113],"ResNet-50":[114],"MMOCR.":[116],"Code":[117],"will":[118],"be":[119],"released":[120],"at:":[121],"https://github.com/ahsdx/DTTR.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}