{"id":"https://openalex.org/W4386453743","doi":"https://doi.org/10.1109/tpami.2023.3312285","title":"SPTS v2: Single-Point Scene Text Spotting","display_name":"SPTS v2: Single-Point Scene Text Spotting","publication_year":2023,"publication_date":"2023-09-05","ids":{"openalex":"https://openalex.org/W4386453743","doi":"https://doi.org/10.1109/tpami.2023.3312285","pmid":"https://pubmed.ncbi.nlm.nih.gov/37669204"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3312285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3312285","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/A5100389396","display_name":"Yuliang Liu","orcid":"https://orcid.org/0000-0002-3037-173X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuliang Liu","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414877","display_name":"Jiaxin Zhang","orcid":"https://orcid.org/0000-0003-2144-9053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxin Zhang","raw_affiliation_strings":["Bytedance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Bytedance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012042767","display_name":"Dezhi Peng","orcid":"https://orcid.org/0000-0002-3263-3449"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Peng","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787743","display_name":"Mingxin Huang","orcid":"https://orcid.org/0009-0002-5736-959X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxin Huang","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352773","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0001-9082-094X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681719","display_name":"Jingqun Tang","orcid":"https://orcid.org/0000-0003-2577-0119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqun Tang","raw_affiliation_strings":["Bytedance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Bytedance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102003518","display_name":"Can Huang","orcid":"https://orcid.org/0009-0006-9126-3069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Can Huang","raw_affiliation_strings":["Bytedance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Bytedance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006294869","display_name":"Chunhua Shen","orcid":"https://orcid.org/0000-0002-8648-8718"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Shen","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100389396"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":5.1755,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96801444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"45","issue":"12","first_page":"15665","last_page":"15679"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9860000014305115,"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":0.9299242496490479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.826556384563446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.599931538105011},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5643882751464844},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47078555822372437},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4490979313850403},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4408232569694519},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41363051533699036},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3835042119026184},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3232163190841675}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9299242496490479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826556384563446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599931538105011},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5643882751464844},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47078555822372437},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4490979313850403},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4408232569694519},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41363051533699036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3835042119026184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3232163190841675},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3312285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3312285","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:37669204","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37669204","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":[],"awards":[{"id":"https://openalex.org/G4189157326","display_name":null,"funder_award_id":"62225603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5777740948","display_name":null,"funder_award_id":"62206104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6852825479","display_name":null,"funder_award_id":"61936003","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W639708223","https://openalex.org/W1521064364","https://openalex.org/W1922126009","https://openalex.org/W1966631307","https://openalex.org/W1972065312","https://openalex.org/W2006653496","https://openalex.org/W2008806374","https://openalex.org/W2122221966","https://openalex.org/W2127141656","https://openalex.org/W2128409098","https://openalex.org/W2144506857","https://openalex.org/W2144554289","https://openalex.org/W2161969291","https://openalex.org/W2194187530","https://openalex.org/W2222512263","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2570343428","https://openalex.org/W2604243686","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2766895242","https://openalex.org/W2777652944","https://openalex.org/W2784050770","https://openalex.org/W2785383245","https://openalex.org/W2810028092","https://openalex.org/W2810983211","https://openalex.org/W2875814315","https://openalex.org/W2906333459","https://openalex.org/W2908510526","https://openalex.org/W2914492226","https://openalex.org/W2962804639","https://openalex.org/W2962935569","https://openalex.org/W2962986948","https://openalex.org/W2963299604","https://openalex.org/W2963648432","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2967615747","https://openalex.org/W2970910956","https://openalex.org/W2981969038","https://openalex.org/W2982770724","https://openalex.org/W2983626510","https://openalex.org/W2988098900","https://openalex.org/W2991626090","https://openalex.org/W2996956254","https://openalex.org/W2997371611","https://openalex.org/W2999874489","https://openalex.org/W3003868038","https://openalex.org/W3003921261","https://openalex.org/W3034772996","https://openalex.org/W3034792612","https://openalex.org/W3034971973","https://openalex.org/W3035452548","https://openalex.org/W3092462694","https://openalex.org/W3093046205","https://openalex.org/W3096609285","https://openalex.org/W3097932944","https://openalex.org/W3102695566","https://openalex.org/W3110398855","https://openalex.org/W3111172959","https://openalex.org/W3152831436","https://openalex.org/W3179426054","https://openalex.org/W3181016597","https://openalex.org/W3181186176","https://openalex.org/W3199245537","https://openalex.org/W4214627427","https://openalex.org/W4225683503","https://openalex.org/W4226013992","https://openalex.org/W4296473552","https://openalex.org/W4304080540","https://openalex.org/W4304091583","https://openalex.org/W4304092561","https://openalex.org/W4310335763","https://openalex.org/W4312230431","https://openalex.org/W4312351507","https://openalex.org/W4312880451","https://openalex.org/W4313013233","https://openalex.org/W4382464147","https://openalex.org/W6620707391","https://openalex.org/W6642972425","https://openalex.org/W6748033758","https://openalex.org/W6752143097","https://openalex.org/W6757320581","https://openalex.org/W6757817989","https://openalex.org/W6772381481","https://openalex.org/W6778485988","https://openalex.org/W6780676603","https://openalex.org/W6784094891","https://openalex.org/W6801512601","https://openalex.org/W6811230874"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W3184921334","https://openalex.org/W4255446307","https://openalex.org/W2033009170","https://openalex.org/W2988098900","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W4362466842"],"abstract_inverted_index":{"End-to-end":[0],"scene":[1,183,199],"text":[2,14,83,98,154,184,200],"spotting":[3,185,201],"has":[4],"made":[5],"significant":[6,196],"progress":[7],"due":[8],"to":[9,51,132,188],"its":[10],"intrinsic":[11],"synergy":[12],"between":[13],"detection":[15],"and":[16,31,120,136],"recognition.":[17],"Previous":[18],"methods":[19],"commonly":[20],"regard":[21],"manual":[22],"annotations":[23],"such":[24],"as":[25,33],"horizontal":[26],"rectangles,":[27,29],"rotated":[28],"quadrangles,":[30],"polygons":[32],"a":[34,57,92,125,176,195],"prerequisite,":[35],"which":[36,102],"are":[37,121],"much":[38],"more":[39],"expensive":[40],"than":[41],"using":[42,56],"single-point.":[43],"Our":[44],"new":[45],"framework,":[46,172],"SPTS":[47,60,147,170],"v2,":[48],"allows":[49],"us":[50],"train":[52],"high-performing":[53],"text-spotting":[54],"models":[55],"single-point":[58,153,180],"annotation.":[59],"v2":[61,148,171],"reserves":[62],"the":[63,66,78,86,105,108,111,117,134,146,166,204],"advantage":[64],"of":[65,81,107,110,168,206],"auto-regressive":[67],"Transformer":[68],"with":[69,91,124,156],"an":[70,192],"Instance":[71],"Assignment":[72],"Decoder":[73,95],"(IAD)":[74],"through":[75],"sequentially":[76],"predicting":[77,88],"center":[79],"points":[80],"all":[82],"instances":[84],"inside":[85],"same":[87,118],"sequence,":[89],"while":[90,159],"Parallel":[93],"Recognition":[94],"(PRD)":[96],"for":[97,179,198],"recognition":[99],"in":[100,182],"parallel,":[101],"significantly":[103],"reduces":[104],"requirement":[106],"length":[109],"sequence.":[112],"These":[113],"two":[114],"decoders":[115],"share":[116],"parameters":[119,158],"interactively":[122],"connected":[123],"simple":[126],"but":[127],"effective":[128],"information":[129],"transmission":[130],"process":[131],"pass":[133],"gradient":[135],"information.":[137],"Comprehensive":[138],"experiments":[139,174],"on":[140],"various":[141],"existing":[142,207],"benchmark":[143],"datasets":[144],"demonstrate":[145],"can":[149],"outperform":[150],"previous":[151],"state-of-the-art":[152],"spotters":[155],"fewer":[157],"achieving":[160],"19\u00d7":[161],"faster":[162],"inference":[163],"speed.":[164],"Within":[165],"context":[167],"our":[169,173],"suggest":[175],"potential":[177],"preference":[178],"representation":[181],"when":[186],"compared":[187],"other":[189],"representations.":[190],"Such":[191],"attempt":[193],"provides":[194],"opportunity":[197],"applications":[202],"beyond":[203],"realms":[205],"paradigms.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}