{"id":"https://openalex.org/W4310335763","doi":"https://doi.org/10.1109/tpami.2022.3223908","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","display_name":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310335763","doi":"https://doi.org/10.1109/tpami.2022.3223908","pmid":"https://pubmed.ncbi.nlm.nih.gov/36417745"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3223908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223908","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5008604905","display_name":"Shancheng Fang","orcid":"https://orcid.org/0000-0002-3100-3664"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shancheng Fang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427468","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-0228-6220"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054311881","display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0003-1204-0512"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["School of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008604905"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":7.1368,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.98062115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"6","first_page":"7123","last_page":"7141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9937999844551086,"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/spotting","display_name":"Spotting","score":0.755150318145752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750757098197937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7021939158439636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5897562503814697},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48817259073257446},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4225972592830658},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37347787618637085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3560958504676819}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.755150318145752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750757098197937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7021939158439636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5897562503814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48817259073257446},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4225972592830658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37347787618637085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3560958504676819}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3223908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3223908","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:36417745","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36417745","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G3316061764","display_name":null,"funder_award_id":"62022076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6179918720","display_name":null,"funder_award_id":"U1936210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7854910236","display_name":null,"funder_award_id":"62222212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G891989852","display_name":null,"funder_award_id":"62102384","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":93,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W1901129140","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2122585011","https://openalex.org/W2127141656","https://openalex.org/W2135231474","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2402268235","https://openalex.org/W2532759528","https://openalex.org/W2555182955","https://openalex.org/W2740767790","https://openalex.org/W2750938222","https://openalex.org/W2777652944","https://openalex.org/W2785383245","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2875814315","https://openalex.org/W2896034938","https://openalex.org/W2896457183","https://openalex.org/W2906333459","https://openalex.org/W2914492226","https://openalex.org/W2928555987","https://openalex.org/W2952285877","https://openalex.org/W2962739339","https://openalex.org/W2962790387","https://openalex.org/W2962986948","https://openalex.org/W2963150697","https://openalex.org/W2963233387","https://openalex.org/W2963517393","https://openalex.org/W2963712589","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2964312704","https://openalex.org/W2965066169","https://openalex.org/W2965463054","https://openalex.org/W2970910956","https://openalex.org/W2981969038","https://openalex.org/W2982770724","https://openalex.org/W2983626510","https://openalex.org/W2988098900","https://openalex.org/W2992505801","https://openalex.org/W2996956254","https://openalex.org/W2997371611","https://openalex.org/W2997749585","https://openalex.org/W2997864923","https://openalex.org/W2998382406","https://openalex.org/W3003218881","https://openalex.org/W3003642782","https://openalex.org/W3003711889","https://openalex.org/W3003921261","https://openalex.org/W3004846386","https://openalex.org/W3005436539","https://openalex.org/W3034447740","https://openalex.org/W3034792612","https://openalex.org/W3034971973","https://openalex.org/W3035106683","https://openalex.org/W3035160371","https://openalex.org/W3035449864","https://openalex.org/W3082397598","https://openalex.org/W3093587902","https://openalex.org/W3097932944","https://openalex.org/W3106271744","https://openalex.org/W3110267192","https://openalex.org/W3110398855","https://openalex.org/W3111172959","https://openalex.org/W3152831436","https://openalex.org/W3159307593","https://openalex.org/W3177318507","https://openalex.org/W3179426054","https://openalex.org/W3181186176","https://openalex.org/W3196976036","https://openalex.org/W3202415716","https://openalex.org/W3202912918","https://openalex.org/W3206651063","https://openalex.org/W4298422451","https://openalex.org/W4385245566","https://openalex.org/W6629590909","https://openalex.org/W6638296183","https://openalex.org/W6727099177","https://openalex.org/W6764306230","https://openalex.org/W6771179582","https://openalex.org/W6780062628","https://openalex.org/W6780226713","https://openalex.org/W6784164614"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W2139675209","https://openalex.org/W2058491579","https://openalex.org/W1483316057"],"abstract_inverted_index":{"Scene":[0],"text":[1,90,184,226,230,260],"spotting":[2,231],"is":[3,128,169,285],"of":[4,17,59,141,154,162,238],"great":[5],"importance":[6],"to":[7,13,22,36,179,188,213,215],"the":[8,39,56,93,102,125,145,152,163,236],"computer":[9],"vision":[10,105],"community":[11],"due":[12],"its":[14,271],"wide":[15],"variety":[16],"applications.":[18],"Recent":[19],"methods":[20],"attempt":[21],"introduce":[23],"linguistic":[24,40],"knowledge":[25],"for":[26,88,144],"challenging":[27],"recognition":[28,227],"rather":[29],"than":[30],"pure":[31],"visual":[32],"classification.":[33],"However,":[34],"how":[35],"effectively":[37,150],"model":[38,75,106,109,127,147],"rules":[41],"in":[42,182,241,252,274],"end-to-end":[43],"deep":[44],"networks":[45],"remains":[46],"a":[47,118,166,197,201,259],"research":[48],"challenge.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,80,136,186],"argue":[54],"that":[55,262],"limited":[57],"capacity":[58],"language":[60,66,74,98,108,126,146,265],"models":[61],"comes":[62],"from":[63,174],"1)":[64],"implicit":[65],"modeling;":[67],"2)":[68],"unidirectional":[69],"feature":[70,133],"representation;":[71],"and":[72,85,107,110,199,203,211,228,254,276],"3)":[73],"with":[76,279],"noise":[77,155],"input.":[78,156],"Correspondingly,":[79],"propose":[81,137,187],"an":[82,138,160],"autonomous,":[83],"bidirectional":[84,120,132],"iterative":[86,142,164],"ABINet++":[87,181,219],"scene":[89,225,229],"spotting.":[91],"First,":[92],"autonomous":[94],"suggests":[95],"enforcing":[96],"explicitly":[97],"modeling":[99,266],"by":[100,192],"decoupling":[101],"recognizer":[103],"into":[104],"blocking":[111],"gradient":[112],"flow":[113],"between":[114],"both":[115,224,273],"models.":[116],"Second,":[117],"novel":[119],"cloze":[121],"network":[122],"(BCN)":[123],"as":[124],"proposed":[129],"based":[130,158],"on":[131,159,223,245],"representation.":[134],"Third,":[135],"execution":[139],"manner":[140],"correction":[143],"which":[148,171,207,233],"can":[149,172,268],"alleviate":[151],"impact":[153],"Additionally,":[157],"ensemble":[161],"predictions,":[165],"self-training":[167],"method":[168,240,267],"developed":[170],"learn":[173],"unlabeled":[175],"images":[176],"effectively.":[177],"Finally,":[178],"polish":[180],"long":[183],"recognition,":[185],"aggregate":[189],"horizontal":[190],"features":[191,217],"embedding":[193],"Transformer":[194],"units":[195],"inside":[196],"U-Net,":[198],"design":[200],"position":[202],"content":[204,212],"attention":[205],"module":[206],"integrates":[208],"character":[209,216],"order":[210],"attend":[214],"precisely.":[218],"achieves":[220],"state-of-the-art":[221],"performance":[222,272],"benchmarks,":[232],"consistently":[234],"demonstrates":[235],"superiority":[237],"our":[239,264],"various":[242],"environments":[243],"especially":[244],"low-quality":[246],"images.":[247],"Besides,":[248],"extensive":[249],"experiments":[250],"including":[251],"English":[253],"Chinese":[255],"also":[256],"prove":[257],"that,":[258],"spotter":[261],"incorporates":[263],"significantly":[269],"improve":[270],"accuracy":[275],"speed":[277],"compared":[278],"commonly":[280],"used":[281],"attention-based":[282],"recognizers.":[283],"Code":[284],"available":[286],"at":[287],"https://github.com/FangShancheng/ABINet-PP.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":15}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}