SVTR: Scene Text Recognition with a Single Visual Model Article Swipe

PDF

Yongkun Du , Zhineng Chen , Caiyan Jia , Xiaoting Yin , Tianlun Zheng , Chenxia Li , Yuning Du , Yu–Gang Jiang ·

YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2205.00159

Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In this study, we propose a Single Visual model for Scene Text recognition within the patch-wise image tokenization framework, which dispenses with the sequential modeling entirely. The method, termed SVTR, firstly decomposes an image text into small patches named character components. Afterward, hierarchical stages are recurrently carried out by component-level mixing, merging and/or combining. Global and local mixing blocks are devised to perceive the inter-character and intra-character patterns, leading to a multi-grained character component perception. Thus, characters are recognized by a simple linear prediction. Experimental results on both English and Chinese scene text recognition tasks demonstrate the effectiveness of SVTR. SVTR-L (Large) achieves highly competitive accuracy in English and outperforms existing methods by a large margin in Chinese, while running faster. In addition, SVTR-T (Tiny) is an effective and much smaller model, which shows appealing speed at inference. The code is publicly available at https://github.com/PaddlePaddle/PaddleOCR.

Related Topics

Computer Science

Artificial Intelligence

Concepts

Computer science Artificial intelligence Character (mathematics) Inference Pattern recognition (psychology) Component (thermodynamics) Feature (linguistics) Code (set theory) Margin (machine learning) Perception Natural language processing Speech recognition Machine learning Set (abstract data type) Mathematics Thermodynamics Biology Neuroscience Programming language Philosophy Linguistics Physics Geometry

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2205.00159
PDF: https://arxiv.org/pdf/2205.00159
OA Status: green
Cited By: 25
Related Works: 10
OpenAlex ID: https://openalex.org/W4308291331

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4308291331

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2205.00159

Digital Object Identifier
Title: SVTR: Scene Text Recognition with a Single Visual Model

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2022

Year of publication
Publication date: 2022-04-30

Full publication date if available
Authors: Yongkun Du, Zhineng Chen, Caiyan Jia, Xiaoting Yin, Tianlun Zheng, Chenxia Li, Yuning Du, Yu–Gang Jiang

List of authors in order
Landing page: https://arxiv.org/abs/2205.00159

Publisher landing page
PDF URL: https://arxiv.org/pdf/2205.00159

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2205.00159

Direct OA link when available
Concepts: Computer science, Artificial intelligence, Character (mathematics), Inference, Pattern recognition (psychology), Component (thermodynamics), Feature (linguistics), Code (set theory), Margin (machine learning), Perception, Natural language processing, Speech recognition, Machine learning, Set (abstract data type), Mathematics, Thermodynamics, Biology, Neuroscience, Programming language, Philosophy, Linguistics, Physics, Geometry

Top concepts (fields/topics) attached by OpenAlex
Cited by: 25

Total citation count in OpenAlex
Citations by year (recent): 2025: 4, 2024: 12, 2023: 9

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4308291331
doi	https://doi.org/10.48550/arxiv.2205.00159
ids.doi	https://doi.org/10.48550/arxiv.2205.00159
ids.openalex	https://openalex.org/W4308291331
fwci
type	preprint
title	SVTR: Scene Text Recognition with a Single Visual Model
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10601
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9995999932289124
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Handwritten Text Recognition Techniques
topics[1].id	https://openalex.org/T10824
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.991599977016449
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	Image Retrieval and Classification Techniques
topics[2].id	https://openalex.org/T11550
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.955299973487854
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Text and Document Classification Technologies
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8300396203994751
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C154945302
concepts[1].level	1
concepts[1].score	0.6297414302825928
concepts[1].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[1].display_name	Artificial intelligence
concepts[2].id	https://openalex.org/C2780861071
concepts[2].level	2
concepts[2].score	0.5911625623703003
concepts[2].wikidata	https://www.wikidata.org/wiki/Q1062934
concepts[2].display_name	Character (mathematics)
concepts[3].id	https://openalex.org/C2776214188
concepts[3].level	2
concepts[3].score	0.5876477956771851
concepts[3].wikidata	https://www.wikidata.org/wiki/Q408386
concepts[3].display_name	Inference
concepts[4].id	https://openalex.org/C153180895
concepts[4].level	2
concepts[4].score	0.4958849847316742
concepts[4].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[4].display_name	Pattern recognition (psychology)
concepts[5].id	https://openalex.org/C168167062
concepts[5].level	2
concepts[5].score	0.4934898614883423
concepts[5].wikidata	https://www.wikidata.org/wiki/Q1117970
concepts[5].display_name	Component (thermodynamics)
concepts[6].id	https://openalex.org/C2776401178
concepts[6].level	2
concepts[6].score	0.4599745273590088
concepts[6].wikidata	https://www.wikidata.org/wiki/Q12050496
concepts[6].display_name	Feature (linguistics)
concepts[7].id	https://openalex.org/C2776760102
concepts[7].level	3
concepts[7].score	0.45932647585868835
concepts[7].wikidata	https://www.wikidata.org/wiki/Q5139990
concepts[7].display_name	Code (set theory)
concepts[8].id	https://openalex.org/C774472
concepts[8].level	2
concepts[8].score	0.451331228017807
concepts[8].wikidata	https://www.wikidata.org/wiki/Q6760393
concepts[8].display_name	Margin (machine learning)
concepts[9].id	https://openalex.org/C26760741
concepts[9].level	2
concepts[9].score	0.4244038462638855
concepts[9].wikidata	https://www.wikidata.org/wiki/Q160402
concepts[9].display_name	Perception
concepts[10].id	https://openalex.org/C204321447
concepts[10].level	1
concepts[10].score	0.3918342590332031
concepts[10].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[10].display_name	Natural language processing
concepts[11].id	https://openalex.org/C28490314
concepts[11].level	1
concepts[11].score	0.3410831689834595
concepts[11].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[11].display_name	Speech recognition
concepts[12].id	https://openalex.org/C119857082
concepts[12].level	1
concepts[12].score	0.2369108498096466
concepts[12].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[12].display_name	Machine learning
concepts[13].id	https://openalex.org/C177264268
concepts[13].level	2
concepts[13].score	0.0
concepts[13].wikidata	https://www.wikidata.org/wiki/Q1514741
concepts[13].display_name	Set (abstract data type)
concepts[14].id	https://openalex.org/C33923547
concepts[14].level	0
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q395
concepts[14].display_name	Mathematics
concepts[15].id	https://openalex.org/C97355855
concepts[15].level	1
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q11473
concepts[15].display_name	Thermodynamics
concepts[16].id	https://openalex.org/C86803240
concepts[16].level	0
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q420
concepts[16].display_name	Biology
concepts[17].id	https://openalex.org/C169760540
concepts[17].level	1
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q207011
concepts[17].display_name	Neuroscience
concepts[18].id	https://openalex.org/C199360897
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[18].display_name	Programming language
concepts[19].id	https://openalex.org/C138885662
concepts[19].level	0
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[19].display_name	Philosophy
concepts[20].id	https://openalex.org/C41895202
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[20].display_name	Linguistics
concepts[21].id	https://openalex.org/C121332964
concepts[21].level	0
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q413
concepts[21].display_name	Physics
concepts[22].id	https://openalex.org/C2524010
concepts[22].level	1
concepts[22].score	0.0
concepts[22].wikidata	https://www.wikidata.org/wiki/Q8087
concepts[22].display_name	Geometry
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8300396203994751
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/artificial-intelligence
keywords[1].score	0.6297414302825928
keywords[1].display_name	Artificial intelligence
keywords[2].id	https://openalex.org/keywords/character
keywords[2].score	0.5911625623703003
keywords[2].display_name	Character (mathematics)
keywords[3].id	https://openalex.org/keywords/inference
keywords[3].score	0.5876477956771851
keywords[3].display_name	Inference
keywords[4].id	https://openalex.org/keywords/pattern-recognition
keywords[4].score	0.4958849847316742
keywords[4].display_name	Pattern recognition (psychology)
keywords[5].id	https://openalex.org/keywords/component
keywords[5].score	0.4934898614883423
keywords[5].display_name	Component (thermodynamics)
keywords[6].id	https://openalex.org/keywords/feature
keywords[6].score	0.4599745273590088
keywords[6].display_name	Feature (linguistics)
keywords[7].id	https://openalex.org/keywords/code
keywords[7].score	0.45932647585868835
keywords[7].display_name	Code (set theory)
keywords[8].id	https://openalex.org/keywords/margin
keywords[8].score	0.451331228017807
keywords[8].display_name	Margin (machine learning)
keywords[9].id	https://openalex.org/keywords/perception
keywords[9].score	0.4244038462638855
keywords[9].display_name	Perception
keywords[10].id	https://openalex.org/keywords/natural-language-processing
keywords[10].score	0.3918342590332031
keywords[10].display_name	Natural language processing
keywords[11].id	https://openalex.org/keywords/speech-recognition
keywords[11].score	0.3410831689834595
keywords[11].display_name	Speech recognition
keywords[12].id	https://openalex.org/keywords/machine-learning
keywords[12].score	0.2369108498096466
keywords[12].display_name	Machine learning
language	en
locations[0].id	pmh:oai:arXiv.org:2205.00159
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/2205.00159
locations[0].version	submittedVersion
locations[0].raw_type
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/2205.00159
locations[1].id	doi:10.48550/arxiv.2205.00159
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.2205.00159
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/A5085282915
authorships[2].author.orcid	https://orcid.org/0000-0003-0650-9564
authorships[2].author.display_name	Caiyan Jia
authorships[2].author_position	middle
authorships[2].raw_author_name	Jia, Caiyan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5034820064
authorships[3].author.orcid	https://orcid.org/0000-0001-7708-7819
authorships[3].author.display_name	Xiaoting Yin
authorships[3].author_position	middle
authorships[3].raw_author_name	Yin, Xiaoting
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5102496363
authorships[4].author.orcid
authorships[4].author.display_name	Tianlun Zheng
authorships[4].author_position	middle
authorships[4].raw_author_name	Zheng, Tianlun
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5103082468
authorships[5].author.orcid	https://orcid.org/0000-0003-0321-5675
authorships[5].author.display_name	Chenxia Li
authorships[5].author_position	middle
authorships[5].raw_author_name	Li, Chenxia
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5010944460
authorships[6].author.orcid	https://orcid.org/0009-0007-4995-5472
authorships[6].author.display_name	Yuning Du
authorships[6].author_position	middle
authorships[6].raw_author_name	Du, Yuning
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5047962986
authorships[7].author.orcid	https://orcid.org/0000-0002-1907-8567
authorships[7].author.display_name	Yu–Gang Jiang
authorships[7].author_position	last
authorships[7].raw_author_name	Jiang, Yu-Gang
authorships[7].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/2205.00159
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	SVTR: Scene Text Recognition with a Single Visual Model
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10601
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9995999932289124
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Handwritten Text Recognition Techniques
related_works	https://openalex.org/W4251972423, https://openalex.org/W1503216044, https://openalex.org/W2393609567, https://openalex.org/W2369369044, https://openalex.org/W2354143083, https://openalex.org/W2372906645, https://openalex.org/W4319998713, https://openalex.org/W2366269494, https://openalex.org/W2353650902, https://openalex.org/W3125011624
cited_by_count	25
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	4
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	12
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	9
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2205.00159
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/2205.00159
best_oa_location.version	submittedVersion
best_oa_location.raw_type
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/2205.00159
primary_location.id	pmh:oai:arXiv.org:2205.00159
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/2205.00159
primary_location.version	submittedVersion
primary_location.raw_type
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/2205.00159
publication_date	2022-04-30
publication_year	2022
referenced_works_count	0
abstract_inverted_index.a	10, 17, 38, 103, 113, 146
abstract_inverted_index.In	33, 154
abstract_inverted_index.an	65, 159
abstract_inverted_index.at	169, 176
abstract_inverted_index.by	81, 112, 145
abstract_inverted_index.in	139, 149
abstract_inverted_index.is	28, 158, 173
abstract_inverted_index.of	131
abstract_inverted_index.on	119
abstract_inverted_index.to	94, 102
abstract_inverted_index.we	36
abstract_inverted_index.The	59, 171
abstract_inverted_index.and	16, 30, 88, 98, 122, 141, 161
abstract_inverted_index.are	77, 92, 110
abstract_inverted_index.for	13, 20, 42
abstract_inverted_index.out	80
abstract_inverted_index.the	47, 55, 96, 129
abstract_inverted_index.two	7
abstract_inverted_index.Text	44
abstract_inverted_index.This	23
abstract_inverted_index.both	120
abstract_inverted_index.code	172
abstract_inverted_index.into	68
abstract_inverted_index.less	31
abstract_inverted_index.much	162
abstract_inverted_index.text	2, 21, 67, 125
abstract_inverted_index.this	34
abstract_inverted_index.with	54
abstract_inverted_index.SVTR,	62
abstract_inverted_index.SVTR.	132
abstract_inverted_index.Scene	43
abstract_inverted_index.Thus,	108
abstract_inverted_index.image	49, 66
abstract_inverted_index.large	147
abstract_inverted_index.local	89
abstract_inverted_index.model	12, 19, 41
abstract_inverted_index.named	71
abstract_inverted_index.scene	1, 124
abstract_inverted_index.shows	166
abstract_inverted_index.small	69
abstract_inverted_index.speed	168
abstract_inverted_index.tasks	127
abstract_inverted_index.which	52, 165
abstract_inverted_index.while	151
abstract_inverted_index.(Tiny)	157
abstract_inverted_index.Global	87
abstract_inverted_index.SVTR-L	133
abstract_inverted_index.SVTR-T	156
abstract_inverted_index.Single	39
abstract_inverted_index.Visual	40
abstract_inverted_index.and/or	85
abstract_inverted_index.blocks	91
abstract_inverted_index.highly	136
abstract_inverted_index.hybrid	24
abstract_inverted_index.linear	115
abstract_inverted_index.margin	148
abstract_inverted_index.mixing	90
abstract_inverted_index.model,	164
abstract_inverted_index.models	4
abstract_inverted_index.simple	114
abstract_inverted_index.stages	76
abstract_inverted_index.study,	35
abstract_inverted_index.termed	61
abstract_inverted_index.visual	11
abstract_inverted_index.within	46
abstract_inverted_index.(Large)	134
abstract_inverted_index.Chinese	123
abstract_inverted_index.English	121, 140
abstract_inverted_index.blocks,	9
abstract_inverted_index.carried	79
abstract_inverted_index.complex	29
abstract_inverted_index.contain	6
abstract_inverted_index.devised	93
abstract_inverted_index.faster.	153
abstract_inverted_index.feature	14
abstract_inverted_index.firstly	63
abstract_inverted_index.leading	101
abstract_inverted_index.merging	84
abstract_inverted_index.method,	60
abstract_inverted_index.methods	144
abstract_inverted_index.mixing,	83
abstract_inverted_index.patches	70
abstract_inverted_index.propose	37
abstract_inverted_index.results	118
abstract_inverted_index.running	152
abstract_inverted_index.smaller	163
abstract_inverted_index.Chinese,	150
abstract_inverted_index.Dominant	0
abstract_inverted_index.accuracy	138
abstract_inverted_index.achieves	135
abstract_inverted_index.although	26
abstract_inverted_index.building	8
abstract_inverted_index.commonly	5
abstract_inverted_index.existing	143
abstract_inverted_index.modeling	57
abstract_inverted_index.perceive	95
abstract_inverted_index.publicly	174
abstract_inverted_index.sequence	18
abstract_inverted_index.accurate,	27
abstract_inverted_index.addition,	155
abstract_inverted_index.appealing	167
abstract_inverted_index.available	175
abstract_inverted_index.character	72, 105
abstract_inverted_index.component	106
abstract_inverted_index.dispenses	53
abstract_inverted_index.effective	160
abstract_inverted_index.entirely.	58
abstract_inverted_index.patterns,	100
abstract_inverted_index.Afterward,	74
abstract_inverted_index.characters	109
abstract_inverted_index.combining.	86
abstract_inverted_index.decomposes	64
abstract_inverted_index.efficient.	32
abstract_inverted_index.extraction	15
abstract_inverted_index.framework,	51
abstract_inverted_index.inference.	170
abstract_inverted_index.patch-wise	48
abstract_inverted_index.recognized	111
abstract_inverted_index.sequential	56
abstract_inverted_index.competitive	137
abstract_inverted_index.components.	73
abstract_inverted_index.demonstrate	128
abstract_inverted_index.outperforms	142
abstract_inverted_index.perception.	107
abstract_inverted_index.prediction.	116
abstract_inverted_index.recognition	3, 45, 126
abstract_inverted_index.recurrently	78
abstract_inverted_index.Experimental	117
abstract_inverted_index.hierarchical	75
abstract_inverted_index.tokenization	50
abstract_inverted_index.architecture,	25
abstract_inverted_index.effectiveness	130
abstract_inverted_index.multi-grained	104
abstract_inverted_index.transcription.	22
abstract_inverted_index.component-level	82
abstract_inverted_index.inter-character	97
abstract_inverted_index.intra-character	99
abstract_inverted_index.https://github.com/PaddlePaddle/PaddleOCR.	177
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	8
citation_normalized_percentile