{"id":"https://openalex.org/W4310283149","doi":"https://doi.org/10.48550/arxiv.2211.13984","title":"Aggregated Text Transformer for Scene Text Detection","display_name":"Aggregated Text Transformer for Scene Text Detection","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4310283149","doi":"https://doi.org/10.48550/arxiv.2211.13984"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.13984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13984","pdf_url":"https://arxiv.org/pdf/2211.13984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.13984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhou, Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047942518","display_name":"Xiangcheng Du","orcid":"https://orcid.org/0000-0002-4268-6114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Xiangcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056833841","display_name":"Yingbin Zheng","orcid":"https://orcid.org/0000-0002-5590-9292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Yingbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625873","display_name":"Cheng Jin","orcid":"https://orcid.org/0000-0003-3063-1957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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":0.9997000098228455,"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":0.9997000098228455,"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":0.9728999733924866,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9595000147819519,"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":0.7381101250648499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7378366589546204},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.677427351474762},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.620819628238678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6001940965652466},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.439276784658432},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42232733964920044},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.41049501299858093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4104790985584259},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37980759143829346},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.356256365776062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10860368609428406},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08291992545127869},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06292411684989929}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7381101250648499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378366589546204},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.677427351474762},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.620819628238678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001940965652466},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.439276784658432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42232733964920044},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.41049501299858093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4104790985584259},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37980759143829346},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.356256365776062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10860368609428406},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08291992545127869},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06292411684989929},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.13984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13984","pdf_url":"https://arxiv.org/pdf/2211.13984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2211.13984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.13984","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.13984","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.13984","pdf_url":"https://arxiv.org/pdf/2211.13984","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":0,"referenced_works":[],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2510680828"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,16,36,42,86,131,134],"multi-scale":[4,31,63],"aggregation":[5],"strategy":[6],"for":[7],"scene":[8,27,99,126],"text":[9,73,79,93,104,127],"detection":[10,128],"in":[11,26],"natural":[12],"images.":[13],"We":[14],"present":[15],"Aggregated":[17],"Text":[18],"TRansformer(ATTR),":[19],"which":[20,111],"is":[21,112],"designed":[22],"to":[23,84],"represent":[24],"texts":[25,100,116],"images":[28],"with":[29,39,50,119],"a":[30],"self-attention":[32],"mechanism.":[33],"Starting":[34],"from":[35],"image":[37,64],"pyramid":[38],"multiple":[40],"resolutions,":[41],"features":[43,83],"are":[44,66],"first":[45],"extracted":[46],"at":[47],"different":[48,89],"scales":[49,90],"shared":[51],"weight":[52],"and":[53,68,91,117],"then":[54],"fed":[55],"into":[56],"an":[57,107],"encoder-decoder":[58],"architecture":[59],"of":[60,75,114,133],"Transformer.":[61],"The":[62,78,95],"representations":[65],"robust":[67],"contain":[69],"rich":[70],"information":[71],"on":[72,124],"contents":[74],"various":[76],"sizes.":[77],"Transformer":[80],"aggregates":[81],"these":[82],"learn":[85],"interaction":[87],"across":[88],"improve":[92],"representation.":[94],"proposed":[96,135],"method":[97],"detects":[98],"by":[101],"representing":[102],"each":[103],"instance":[105],"as":[106],"individual":[108],"binary":[109],"mask,":[110],"tolerant":[113],"curve":[115],"regions":[118],"dense":[120],"instances.":[121],"Extensive":[122],"experiments":[123],"public":[125],"datasets":[129],"demonstrate":[130],"effectiveness":[132],"framework.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}