{"id":"https://openalex.org/W4385767967","doi":"https://doi.org/10.24963/ijcai.2023/197","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","display_name":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767967","doi":"https://doi.org/10.24963/ijcai.2023/197"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/197","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/197","pdf_url":"https://www.ijcai.org/proceedings/2023/0197.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0197.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102496363","display_name":"Tianlun Zheng","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":"Tianlun Zheng","raw_affiliation_strings":["Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012931772","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0002-0182-3207"},"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":"Zhineng Chen","raw_affiliation_strings":["Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036032938","display_name":"Jinfeng Bai","orcid":"https://orcid.org/0000-0001-8940-480X"},"institutions":[{"id":"https://openalex.org/I4210154505","display_name":"Tomorrows Children\u2019s Fund","ror":"https://ror.org/04wgs4413","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210154505"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["Tomorrow Advance Life"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomorrow Advance Life","institution_ids":["https://openalex.org/I4210154505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101832741","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0003-2311-9082"},"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":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"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":"Yu-Gang Jiang","raw_affiliation_strings":["Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1777","last_page":"1785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9855999946594238,"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":0.9803000092506409,"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":0.8226184248924255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5966911315917969},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.5925452709197998},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5247112512588501},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4906076490879059},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40591299533843994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3470827043056488},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34588056802749634},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33384162187576294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226184248924255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5966911315917969},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.5925452709197998},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5247112512588501},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4906076490879059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40591299533843994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3470827043056488},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34588056802749634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33384162187576294},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/197","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/197","pdf_url":"https://www.ijcai.org/proceedings/2023/0197.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/197","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/197","pdf_url":"https://www.ijcai.org/proceedings/2023/0197.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767967.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2128409098","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2555182955","https://openalex.org/W2593572697","https://openalex.org/W2750938222","https://openalex.org/W2788069964","https://openalex.org/W2810983211","https://openalex.org/W2884585870","https://openalex.org/W2896034938","https://openalex.org/W2963233387","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2983626510","https://openalex.org/W2997864923","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3005436539","https://openalex.org/W3021481629","https://openalex.org/W3035449864","https://openalex.org/W3092309237","https://openalex.org/W3094502228","https://openalex.org/W3110267192","https://openalex.org/W3173990630","https://openalex.org/W3202415716","https://openalex.org/W3202912918","https://openalex.org/W4226329156","https://openalex.org/W4283821822","https://openalex.org/W4287183355","https://openalex.org/W4292825881","https://openalex.org/W4308291331","https://openalex.org/W4310335763","https://openalex.org/W4312298799","https://openalex.org/W4322832305","https://openalex.org/W4386410320"],"related_works":["https://openalex.org/W2355499516","https://openalex.org/W3174480258","https://openalex.org/W3210974833","https://openalex.org/W2599000612","https://openalex.org/W2811475781","https://openalex.org/W2094246381","https://openalex.org/W2361137193","https://openalex.org/W2377736761","https://openalex.org/W2353928006","https://openalex.org/W2797910360"],"abstract_inverted_index":{"Text":[0],"irregularities":[1],"pose":[2],"significant":[3],"challenges":[4],"to":[5,20,48,71,121],"scene":[6],"text":[7,38,43,72,116],"recognizers.":[8,182],"Thin-Plate":[9],"Spline":[10],"(TPS)-based":[11],"rectification":[12,73,141],"is":[13,98,119,184],"widely":[14],"regarded":[15],"as":[16,83],"an":[17,62],"effective":[18],"means":[19],"deal":[21],"with":[22,133],"them.":[23],"Currently,":[24],"the":[25,34,42,68,75,80,124,130,134,140,168],"calculation":[26,82],"of":[27,36,87,154],"TPS":[28,64],"transformation":[29,65],"parameters":[30,155],"purely":[31],"depends":[32],"on":[33,160,178],"quality":[35],"regressed":[37],"borders.":[39],"It":[40],"ignores":[41],"content":[44],"and":[45,92,138,156,170,181],"often":[46],"leads":[47],"unsatisfactory":[49],"rectified":[50],"results":[51],"for":[52,74],"severely":[53],"distorted":[54],"text.":[55],"In":[56],"this":[57],"work,":[58],"we":[59],"introduce":[60],"TPS++,":[61],"attention-enhanced":[63],"that":[66,118,164],"incorporates":[67],"attention":[69,94],"mechanism":[70],"first":[76],"time.":[77,158],"TPS++":[78,106,128,165],"formulates":[79],"parameter":[81],"a":[84,101,108,114,149],"joint":[85],"process":[86],"foreground":[88],"control":[89],"point":[90],"regression":[91],"content-based":[93],"score":[95],"estimation,":[96],"which":[97],"computed":[99],"by":[100,123],"dedicated":[102],"designed":[103],"gated-attention":[104],"block.":[105],"builds":[107],"more":[109],"flexible":[110],"content-aware":[111],"rectifier,":[112],"generating":[113],"natural":[115],"correction":[117],"easier":[120],"read":[122],"subsequent":[125],"recognizer.":[126],"Moreover,":[127],"shares":[129],"feature":[131],"backbone":[132],"recognizer":[135],"in":[136,152],"part":[137],"implements":[139],"at":[142,185],"feature-level":[143],"rather":[144],"than":[145],"image-level,":[146],"incurring":[147],"only":[148],"small":[150],"overhead":[151],"terms":[153],"inference":[157],"Experiments":[159],"public":[161],"benchmarks":[162],"show":[163],"consistently":[166],"improves":[167],"recognition":[169],"achieves":[171],"state-of-the-art":[172],"accuracy.":[173],"Meanwhile,":[174],"it":[175],"generalizes":[176],"well":[177],"different":[179],"backbones":[180],"Code":[183],"https://github.com/simplify23/TPS_PP.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}