{"id":"https://openalex.org/W4404986866","doi":"https://doi.org/10.1109/iccv51701.2025.01874","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","display_name":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404986866","doi":"https://doi.org/10.1109/iccv51701.2025.01874"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.15858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102915298","display_name":"Yongkun Du","orcid":"https://orcid.org/0009-0005-3114-2188"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Du","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University","institution_ids":["https://openalex.org/I4210139618"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085282915","display_name":"Caiyan Jia","orcid":"https://orcid.org/0000-0003-0650-9564"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiyan Jia","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"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/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University","institution_ids":["https://openalex.org/I4210139618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20147","last_page":"20156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9815999865531921,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9815999865531921,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9799000024795532,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9320999979972839,"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":0.7564139366149902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.644904375076294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5867303013801575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4201323091983795},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3681372404098511},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35882246494293213},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.04807063937187195}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7564139366149902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644904375076294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5867303013801575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4201323091983795},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3681372404098511},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35882246494293213},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.04807063937187195}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.15858","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15858","pdf_url":"https://arxiv.org/pdf/2411.15858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.15858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.15858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.15858","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15858","pdf_url":"https://arxiv.org/pdf/2411.15858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2038760474","display_name":null,"funder_award_id":"62427819,32341012,62172103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"},{"id":"https://openalex.org/G7623678150","display_name":null,"funder_award_id":"62427819","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7791778128","display_name":null,"funder_award_id":"32341012","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404986866.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1],"classification":[2],"(CTC)-based":[3],"scene":[4],"text":[5,52,73,88,97,189],"recognition":[6],"(STR)":[7],"methods,":[8],"e.g.,":[9],"SVTR,":[10],"are":[11],"widely":[12],"employed":[13],"in":[14,166,205],"OCR":[15],"applications,":[16],"mainly":[17],"due":[18,48],"to":[19,49,71,86,90,106,139,178],"their":[20],"simple":[21],"architecture,":[22],"which":[23],"only":[24],"contains":[25],"a":[26,30,64,80,102,124],"visual":[27,109,134],"model":[28,66,76,138],"and":[29,34,54,75,155,169,194,209],"CTC-aligned":[31],"linear":[32],"classifier,":[33],"therefore":[35],"fast":[36],"inference.":[37],"However,":[38],"they":[39],"generally":[40],"exhibit":[41],"worse":[42],"accuracy":[43,144,208],"than":[44],"encoder-decoder-based":[45],"methods":[46],"(EDTRs)":[47],"struggling":[50],"with":[51,68],"irregularity":[53],"linguistic":[55,77,130],"missing.":[56],"To":[57],"address":[58],"these":[59],"challenges,":[60],"we":[61,100,122],"propose":[62,123],"SVTRv2,":[63],"CTC":[65,137],"endowed":[67],"the":[69,112,118,133,152,159,203],"ability":[70],"handle":[72],"irregularities":[74],"context.":[78],"First,":[79],"multi-size":[81],"resizing":[82],"strategy":[83],"is":[84,175],"proposed":[85],"resize":[87],"instances":[89],"appropriate":[91],"predefined":[92],"sizes,":[93],"effectively":[94],"avoiding":[95],"severe":[96],"distortion.":[98],"Meanwhile,":[99],"introduce":[101],"feature":[103],"rearrangement":[104],"module":[105,147],"ensure":[107],"that":[108],"features":[110],"accommodate":[111],"requirement":[113],"of":[114,188,207],"CTC,":[115],"thus":[116],"alleviating":[117],"alignment":[119],"puzzle.":[120],"Second,":[121],"semantic":[125],"guidance":[126],"module.":[127],"It":[128],"integrates":[129],"context":[131],"into":[132],"features,":[135],"allowing":[136],"leverage":[140],"language":[141],"information":[142],"for":[143],"improvement.":[145],"This":[146],"can":[148],"be":[149],"omitted":[150],"at":[151],"inference":[153,210],"stage":[154],"would":[156],"not":[157],"increase":[158],"time":[160],"cost.":[161],"We":[162],"extensively":[163],"evaluate":[164],"SVTRv2":[165,174,198],"both":[167],"standard":[168],"recent":[170],"challenging":[171],"benchmarks,":[172],"where":[173],"fairly":[176],"compared":[177],"popular":[179],"STR":[180],"models":[181],"across":[182,202],"multiple":[183],"scenarios,":[184],"including":[185],"different":[186],"types":[187],"irregularity,":[190],"languages,":[191],"long":[192],"text,":[193],"whether":[195],"employing":[196],"pretraining.":[197],"surpasses":[199],"most":[200],"EDTRs":[201],"scenarios":[204],"terms":[206],"speed.":[211],"Code:":[212],"https://github.com/Topdu/OpenOCR.":[213]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}