SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition Article Swipe
Yongkun Du
,
Zhineng Chen
,
Hongtao Xie
,
Caiyan Jia
,
Yu–Gang Jiang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2411.15858
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2411.15858
Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture, which only contains a visual model and a CTC-aligned linear classifier, and therefore fast inference. However, they generally exhibit worse accuracy than encoder-decoder-based methods (EDTRs) due to struggling with text irregularity and linguistic missing. To address these challenges, we propose SVTRv2, a CTC model endowed with the ability to handle text irregularities and model linguistic context. First, a multi-size resizing strategy is proposed to resize text instances to appropriate predefined sizes, effectively avoiding severe text distortion. Meanwhile, we introduce a feature rearrangement module to ensure that visual features accommodate the requirement of CTC, thus alleviating the alignment puzzle. Second, we propose a semantic guidance module. It integrates linguistic context into the visual features, allowing CTC model to leverage language information for accuracy improvement. This module can be omitted at the inference stage and would not increase the time cost. We extensively evaluate SVTRv2 in both standard and recent challenging benchmarks, where SVTRv2 is fairly compared to popular STR models across multiple scenarios, including different types of text irregularity, languages, long text, and whether employing pretraining. SVTRv2 surpasses most EDTRs across the scenarios in terms of accuracy and inference speed. Code: https://github.com/Topdu/OpenOCR.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2411.15858
- https://arxiv.org/pdf/2411.15858
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404986866
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404986866Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2411.15858Digital Object Identifier
- Title
-
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text RecognitionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-11-24Full publication date if available
- Authors
-
Yongkun Du, Zhineng Chen, Hongtao Xie, Caiyan Jia, Yu–Gang JiangList of authors in order
- Landing page
-
https://arxiv.org/abs/2411.15858Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2411.15858Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2411.15858Direct OA link when available
- Concepts
-
Encoder, Computer science, Speech recognition, Artificial intelligence, Computer vision, Pattern recognition (psychology), Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4404986866 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2411.15858 |
| ids.doi | https://doi.org/10.48550/arxiv.2411.15858 |
| ids.openalex | https://openalex.org/W4404986866 |
| fwci | |
| type | preprint |
| title | SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10201 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9815999865531921 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Speech Recognition and Synthesis |
| topics[1].id | https://openalex.org/T10601 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9799000024795532 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Handwritten Text Recognition Techniques |
| topics[2].id | https://openalex.org/T14339 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9320999979972839 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Image Processing and 3D Reconstruction |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C118505674 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7564139366149902 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[0].display_name | Encoder |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.644904375076294 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C28490314 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5867303013801575 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[2].display_name | Speech recognition |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4201323091983795 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C31972630 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3681372404098511 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[4].display_name | Computer vision |
| concepts[5].id | https://openalex.org/C153180895 |
| concepts[5].level | 2 |
| concepts[5].score | 0.35882246494293213 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[5].display_name | Pattern recognition (psychology) |
| concepts[6].id | https://openalex.org/C111919701 |
| concepts[6].level | 1 |
| concepts[6].score | 0.04807063937187195 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[6].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/encoder |
| keywords[0].score | 0.7564139366149902 |
| keywords[0].display_name | Encoder |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.644904375076294 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/speech-recognition |
| keywords[2].score | 0.5867303013801575 |
| keywords[2].display_name | Speech recognition |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.4201323091983795 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/computer-vision |
| keywords[4].score | 0.3681372404098511 |
| keywords[4].display_name | Computer vision |
| keywords[5].id | https://openalex.org/keywords/pattern-recognition |
| keywords[5].score | 0.35882246494293213 |
| keywords[5].display_name | Pattern recognition (psychology) |
| keywords[6].id | https://openalex.org/keywords/operating-system |
| keywords[6].score | 0.04807063937187195 |
| keywords[6].display_name | Operating system |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2411.15858 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2411.15858 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2411.15858 |
| locations[1].id | doi:10.48550/arxiv.2411.15858 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2411.15858 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102915298 |
| authorships[0].author.orcid | https://orcid.org/0009-0000-9859-721X |
| authorships[0].author.display_name | Yongkun Du |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Du, Yongkun |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5080463909 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1543-6889 |
| authorships[1].author.display_name | Zhineng Chen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chen, Zhineng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5078162380 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6249-5315 |
| authorships[2].author.display_name | Hongtao Xie |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xie, Hongtao |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5085282915 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-0650-9564 |
| authorships[3].author.display_name | Caiyan Jia |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jia, Caiyan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5047962986 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-1907-8567 |
| authorships[4].author.display_name | Yu–Gang Jiang |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Jiang, Yu-Gang |
| authorships[4].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2411.15858 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10201 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9815999865531921 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Speech Recognition and Synthesis |
| 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 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2411.15858 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2411.15858 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2411.15858 |
| primary_location.id | pmh:oai:arXiv.org:2411.15858 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2411.15858 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2411.15858 |
| publication_date | 2024-11-24 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 26, 30, 64, 80, 102, 124 |
| abstract_inverted_index.It | 128 |
| abstract_inverted_index.To | 57 |
| abstract_inverted_index.We | 162 |
| abstract_inverted_index.at | 151 |
| abstract_inverted_index.be | 149 |
| abstract_inverted_index.in | 14, 166, 205 |
| abstract_inverted_index.is | 84, 175 |
| abstract_inverted_index.of | 114, 188, 207 |
| abstract_inverted_index.to | 19, 49, 71, 86, 90, 106, 139, 178 |
| abstract_inverted_index.we | 61, 100, 122 |
| abstract_inverted_index.CTC | 65, 137 |
| abstract_inverted_index.OCR | 15 |
| abstract_inverted_index.STR | 180 |
| abstract_inverted_index.and | 29, 34, 54, 75, 155, 169, 194, 209 |
| abstract_inverted_index.are | 11 |
| abstract_inverted_index.can | 148 |
| abstract_inverted_index.due | 18, 48 |
| abstract_inverted_index.for | 143 |
| abstract_inverted_index.not | 157 |
| abstract_inverted_index.the | 69, 112, 118, 133, 152, 159, 203 |
| abstract_inverted_index.CTC, | 115 |
| abstract_inverted_index.This | 146 |
| abstract_inverted_index.both | 167 |
| abstract_inverted_index.fast | 36 |
| abstract_inverted_index.into | 132 |
| abstract_inverted_index.long | 192 |
| abstract_inverted_index.most | 200 |
| abstract_inverted_index.only | 24 |
| abstract_inverted_index.text | 5, 52, 73, 88, 97, 189 |
| abstract_inverted_index.than | 44 |
| abstract_inverted_index.that | 108 |
| abstract_inverted_index.they | 39 |
| abstract_inverted_index.thus | 116 |
| abstract_inverted_index.time | 160 |
| abstract_inverted_index.with | 51, 68 |
| abstract_inverted_index.(STR) | 7 |
| abstract_inverted_index.Code: | 212 |
| abstract_inverted_index.EDTRs | 201 |
| abstract_inverted_index.SVTR, | 10 |
| abstract_inverted_index.cost. | 161 |
| abstract_inverted_index.e.g., | 9 |
| abstract_inverted_index.model | 28, 66, 76, 138 |
| abstract_inverted_index.scene | 4 |
| abstract_inverted_index.stage | 154 |
| abstract_inverted_index.terms | 206 |
| abstract_inverted_index.text, | 193 |
| abstract_inverted_index.their | 20 |
| abstract_inverted_index.these | 59 |
| abstract_inverted_index.types | 187 |
| abstract_inverted_index.where | 173 |
| abstract_inverted_index.which | 23 |
| abstract_inverted_index.worse | 42 |
| abstract_inverted_index.would | 156 |
| abstract_inverted_index.First, | 79 |
| abstract_inverted_index.SVTRv2 | 165, 174, 198 |
| abstract_inverted_index.across | 182, 202 |
| abstract_inverted_index.ensure | 107 |
| abstract_inverted_index.fairly | 176 |
| abstract_inverted_index.handle | 72 |
| abstract_inverted_index.linear | 32 |
| abstract_inverted_index.mainly | 17 |
| abstract_inverted_index.models | 181 |
| abstract_inverted_index.module | 105, 147 |
| abstract_inverted_index.recent | 170 |
| abstract_inverted_index.resize | 87 |
| abstract_inverted_index.severe | 96 |
| abstract_inverted_index.simple | 21 |
| abstract_inverted_index.sizes, | 93 |
| abstract_inverted_index.speed. | 211 |
| abstract_inverted_index.visual | 27, 109, 134 |
| abstract_inverted_index.widely | 12 |
| abstract_inverted_index.(EDTRs) | 47 |
| abstract_inverted_index.SVTRv2, | 63 |
| abstract_inverted_index.Second, | 121 |
| abstract_inverted_index.ability | 70 |
| abstract_inverted_index.address | 58 |
| abstract_inverted_index.context | 131 |
| abstract_inverted_index.endowed | 67 |
| abstract_inverted_index.exhibit | 41 |
| abstract_inverted_index.feature | 103 |
| abstract_inverted_index.methods | 46 |
| abstract_inverted_index.module. | 127 |
| abstract_inverted_index.omitted | 150 |
| abstract_inverted_index.popular | 179 |
| abstract_inverted_index.propose | 62, 123 |
| abstract_inverted_index.puzzle. | 120 |
| abstract_inverted_index.whether | 195 |
| abstract_inverted_index.However, | 38 |
| abstract_inverted_index.accuracy | 43, 144, 208 |
| abstract_inverted_index.allowing | 136 |
| abstract_inverted_index.avoiding | 95 |
| abstract_inverted_index.compared | 177 |
| abstract_inverted_index.contains | 25 |
| abstract_inverted_index.context. | 78 |
| abstract_inverted_index.employed | 13 |
| abstract_inverted_index.evaluate | 164 |
| abstract_inverted_index.features | 110 |
| abstract_inverted_index.guidance | 126 |
| abstract_inverted_index.increase | 158 |
| abstract_inverted_index.language | 141 |
| abstract_inverted_index.leverage | 140 |
| abstract_inverted_index.methods, | 8 |
| abstract_inverted_index.missing. | 56 |
| abstract_inverted_index.multiple | 183 |
| abstract_inverted_index.proposed | 85 |
| abstract_inverted_index.resizing | 82 |
| abstract_inverted_index.semantic | 125 |
| abstract_inverted_index.standard | 168 |
| abstract_inverted_index.strategy | 83 |
| abstract_inverted_index.temporal | 1 |
| abstract_inverted_index.alignment | 119 |
| abstract_inverted_index.different | 186 |
| abstract_inverted_index.employing | 196 |
| abstract_inverted_index.features, | 135 |
| abstract_inverted_index.generally | 40 |
| abstract_inverted_index.including | 185 |
| abstract_inverted_index.inference | 153, 210 |
| abstract_inverted_index.instances | 89 |
| abstract_inverted_index.introduce | 101 |
| abstract_inverted_index.scenarios | 204 |
| abstract_inverted_index.surpasses | 199 |
| abstract_inverted_index.therefore | 35 |
| abstract_inverted_index.Meanwhile, | 99 |
| abstract_inverted_index.inference. | 37 |
| abstract_inverted_index.integrates | 129 |
| abstract_inverted_index.languages, | 191 |
| abstract_inverted_index.linguistic | 55, 77, 130 |
| abstract_inverted_index.multi-size | 81 |
| abstract_inverted_index.predefined | 92 |
| abstract_inverted_index.scenarios, | 184 |
| abstract_inverted_index.struggling | 50 |
| abstract_inverted_index.(CTC)-based | 3 |
| abstract_inverted_index.CTC-aligned | 31 |
| abstract_inverted_index.accommodate | 111 |
| abstract_inverted_index.alleviating | 117 |
| abstract_inverted_index.appropriate | 91 |
| abstract_inverted_index.benchmarks, | 172 |
| abstract_inverted_index.challenges, | 60 |
| abstract_inverted_index.challenging | 171 |
| abstract_inverted_index.classifier, | 33 |
| abstract_inverted_index.distortion. | 98 |
| abstract_inverted_index.effectively | 94 |
| abstract_inverted_index.extensively | 163 |
| abstract_inverted_index.information | 142 |
| abstract_inverted_index.recognition | 6 |
| abstract_inverted_index.requirement | 113 |
| abstract_inverted_index.improvement. | 145 |
| abstract_inverted_index.irregularity | 53 |
| abstract_inverted_index.pretraining. | 197 |
| abstract_inverted_index.Connectionist | 0 |
| abstract_inverted_index.applications, | 16 |
| abstract_inverted_index.architecture, | 22 |
| abstract_inverted_index.irregularity, | 190 |
| abstract_inverted_index.rearrangement | 104 |
| abstract_inverted_index.classification | 2 |
| abstract_inverted_index.irregularities | 74 |
| abstract_inverted_index.encoder-decoder-based | 45 |
| abstract_inverted_index.https://github.com/Topdu/OpenOCR. | 213 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |