{"id":"https://openalex.org/W4379984742","doi":"https://doi.org/10.1109/tcsvt.2023.3285096","title":"Text Position-Aware Pixel Aggregation Network With Adaptive Gaussian Threshold: Detecting Text in the Wild","display_name":"Text Position-Aware Pixel Aggregation Network With Adaptive Gaussian Threshold: Detecting Text in the Wild","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4379984742","doi":"https://doi.org/10.1109/tcsvt.2023.3285096"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3285096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3285096","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5101443309","display_name":"Jiayu Xu","orcid":"https://orcid.org/0000-0001-9305-2798"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiayu Xu","raw_affiliation_strings":["Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037470476","display_name":"Ailiang Lin","orcid":"https://orcid.org/0000-0002-2118-5409"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ailiang Lin","raw_affiliation_strings":["Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753458","display_name":"Jinxing Li","orcid":"https://orcid.org/0000-0001-5156-0305"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxing Li","raw_affiliation_strings":["Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Medical Biometrics Perception and Analysis Engineering Laboratory, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030843117","display_name":"Guangming Lu","orcid":"https://orcid.org/0000-0003-1578-2634"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Lu","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology at Shenzhen, Shenzhen, China","Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology at Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101443309"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.0789,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79129356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"34","issue":"1","first_page":"286","last_page":"298"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9925000071525574,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.980400025844574,"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/computer-science","display_name":"Computer science","score":0.7806767225265503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7189481258392334},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6477274894714355},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6131614446640015},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5821651220321655},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5752848982810974},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5582270622253418},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5576919317245483},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5317140221595764},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5141963958740234},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5131919980049133},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5033397078514099},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4960575997829437},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49560344219207764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47588884830474854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.450960248708725},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2987154722213745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14207512140274048},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08246797323226929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806767225265503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7189481258392334},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6477274894714355},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6131614446640015},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5821651220321655},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5752848982810974},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5582270622253418},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5576919317245483},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5317140221595764},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5141963958740234},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5131919980049133},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5033397078514099},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4960575997829437},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49560344219207764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47588884830474854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.450960248708725},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2987154722213745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14207512140274048},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08246797323226929},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3285096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3285096","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G333909914","display_name":null,"funder_award_id":"61906162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5694134097","display_name":null,"funder_award_id":"JCYJ20210324132210025","funder_id":"https://openalex.org/F4320335803","funder_display_name":"Shenzhen Fundamental Research and Discipline Layout project"},{"id":"https://openalex.org/G5726720604","display_name":null,"funder_award_id":"62176077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6291376620","display_name":null,"funder_award_id":"RCBS20200714114910193","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"},{"id":"https://openalex.org/G6613849761","display_name":null,"funder_award_id":"62272133","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"},{"id":"https://openalex.org/F4320335803","display_name":"Shenzhen Fundamental Research and Discipline Layout project","ror":null},{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1972065312","https://openalex.org/W1988461287","https://openalex.org/W2074849287","https://openalex.org/W2111993661","https://openalex.org/W2137969867","https://openalex.org/W2138326121","https://openalex.org/W2144554289","https://openalex.org/W2187089797","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2593539516","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2772800855","https://openalex.org/W2784050770","https://openalex.org/W2810028092","https://openalex.org/W2831607544","https://openalex.org/W2902494497","https://openalex.org/W2953606406","https://openalex.org/W2953894958","https://openalex.org/W2962810613","https://openalex.org/W2963299604","https://openalex.org/W2963353821","https://openalex.org/W2963398399","https://openalex.org/W2963516811","https://openalex.org/W2963647456","https://openalex.org/W2963840241","https://openalex.org/W2964294787","https://openalex.org/W2964685115","https://openalex.org/W2967155990","https://openalex.org/W2967591398","https://openalex.org/W2967615747","https://openalex.org/W2980358704","https://openalex.org/W2989889352","https://openalex.org/W2991626090","https://openalex.org/W2998621280","https://openalex.org/W3024377038","https://openalex.org/W3034230962","https://openalex.org/W3034514377","https://openalex.org/W3034792612","https://openalex.org/W3035679705","https://openalex.org/W3082397598","https://openalex.org/W3092156752","https://openalex.org/W3092619320","https://openalex.org/W3092834961","https://openalex.org/W3101769104","https://openalex.org/W3102695566","https://openalex.org/W3106228955","https://openalex.org/W3106250896","https://openalex.org/W3138516171","https://openalex.org/W3138649552","https://openalex.org/W3159307593","https://openalex.org/W3172799005","https://openalex.org/W3175515048","https://openalex.org/W3181016597","https://openalex.org/W3186906052","https://openalex.org/W3189348500","https://openalex.org/W3192658445","https://openalex.org/W4214922754","https://openalex.org/W4226334005","https://openalex.org/W4297426812","https://openalex.org/W6620707391","https://openalex.org/W6746206475","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Over":[0],"recent":[1],"years,":[2],"deep":[3],"learning":[4],"has":[5,125],"significantly":[6],"boosted":[7],"scene":[8,15,60,133],"text":[9,16,46,61,94,106,115,134],"detection":[10],"performance,":[11],"and":[12,111,131],"current":[13],"segmentation-based":[14],"detectors":[17],"can":[18],"achieve":[19],"compact":[20],"bounding":[21],"boxes":[22],"for":[23,37],"irregular":[24],"texts.":[25],"However,":[26],"it":[27],"is":[28,75],"also":[29],"challenging":[30],"to":[31,42,90],"tackle":[32],"crowded":[33],"or":[34],"overlapping":[35],"texts":[36],"these":[38,53],"existing":[39],"methods":[40],"due":[41],"conglutination":[43],"between":[44],"adjacent":[45],"instances":[47],"in":[48,83,108],"segmentation":[49],"results.":[50],"To":[51],"address":[52],"issues,":[54],"we":[55],"propose":[56],"a":[57,71,80],"more":[58,92,113],"accurate":[59,93,114],"detector,":[62],"Text":[63,85,97],"Position-Aware":[64,98],"Pixel":[65,100],"Aggregation":[66,101],"Network,":[67],"termed":[68],"TPPAN.":[69],"Specifically,":[70],"Gaussian":[72],"threshold":[73],"representation":[74],"adaptively":[76],"learned":[77],"instead":[78],"of":[79],"constant":[81],"setting":[82],"Adaptively":[84],"Kernel":[86],"Thresholding":[87],"(ATKT)":[88],"module":[89,103],"obtain":[91],"kernels.":[95],"Then":[96],"Region":[99],"(TPAR-PA)":[102],"predicts":[104],"the":[105,122],"regions":[107],"relative":[109],"positions":[110],"generates":[112],"contours.":[116],"Adequate":[117],"experiments":[118],"have":[119],"demonstrated":[120],"that":[121],"resulting":[123],"detector":[124],"achieved":[126],"state-of-the-art":[127],"performance":[128],"on":[129],"multi-oriented":[130],"curved":[132],"benchmarks.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}