Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Scene Text Recognition
/
ICDAR2015
Scene Text Recognition on ICDAR2015
Metric: Accuracy (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide extra data
Export CSV
Sort:
Accuracy (best first)
Accuracy (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Accuracy
▼
Extra Data
Paper
Date
↕
Code
1
DTrOCR 105M
93.5
No
DTrOCR: Decoder-only Transformer for Optical Cha...
2023-08-30
Code
2
CLIP4STR-L*
92.6
Yes
An Empirical Study of Scaling Law for OCR
2023-12-29
Code
3
CPPD
91.7
Yes
Context Perception Parallel Decoder for Scene Te...
2023-07-23
Code
4
CLIP4STR-L (DataComp-1B)
91.4
No
CLIP4STR: A Simple Baseline for Scene Text Recog...
2023-05-23
Code
5
MGP-STR
90.9
Yes
Multi-Granularity Prediction for Scene Text Reco...
2022-09-08
Code
6
CLIP4STR-L
90.8
Yes
CLIP4STR: A Simple Baseline for Scene Text Recog...
2023-05-23
Code
7
CLIP4STR-B
90.6
Yes
CLIP4STR: A Simple Baseline for Scene Text Recog...
2023-05-23
Code
8
SIGA_S
87.6
No
Self-supervised Implicit Glyph Attention for Tex...
2022-03-07
Code
9
S-GTR
87.3
Yes
Visual Semantics Allow for Textual Reasoning Bet...
2021-12-24
Code
10
MATRN
86.6
No
Multi-modal Text Recognition Networks: Interacti...
2021-11-30
Code
11
CDistNet (Ours)
86.25
No
CDistNet: Perceiving Multi-Domain Character Dist...
2021-11-22
Code
12
DiffusionSTR
86
No
DiffusionSTR: Diffusion Model for Scene Text Rec...
2023-06-29
-
13
DPAN
85.5
No
-
-
Code
14
RCEED
82.2
No
Representation and Correlation Enhanced Encoder-...
2021-06-13
Code
15
CSTR
81.6
No
Revisiting Classification Perspective on Scene T...
2021-02-22
Code
16
Yet Another Text Recognizer
80.2
No
Why You Should Try the Real Data for the Scene T...
2021-07-29
Code
17
SEED
80
No
SEED: Semantics Enhanced Encoder-Decoder Framewo...
2020-05-22
Code
18
TextScanner
79.4
No
TextScanner: Reading Characters in Order for Rob...
2019-12-28
-
19
SATRN
79
No
On Recognizing Texts of Arbitrary Shapes with 2D...
2019-10-10
Code
20
SAFL
77.5
No
SAFL: A Self-Attention Scene Text Recognizer wit...
2022-01-01
Code
21
ASTER
76.1
No
-
-
Code
22
DAN
74.5
No
Decoupled Attention Network for Text Recognition
2019-12-21
Code
23
AON
73
No
AON: Towards Arbitrarily-Oriented Text Recognition
2017-11-12
Code
24
ViTSTR
72.6
No
Vision Transformer for Fast and Efficient Scene ...
2021-05-18
Code
25
Baek et al.
71.8
No
What Is Wrong With Scene Text Recognition Model ...
2019-04-03
Code
26
SAR
69.2
No
Show, Attend and Read: A Simple and Strong Basel...
2018-11-02
Code
#1
DTrOCR 105M
SOTA
93.5
Accuracy
· 2023-08-30
DTrOCR: Decoder-only Transformer for Optical Character Recognition
Code
#2
CLIP4STR-L*
92.6
Accuracy
· Extra Data
· 2023-12-29
An Empirical Study of Scaling Law for OCR
Code
#3
CPPD
SOTA
91.7
Accuracy
· Extra Data
· 2023-07-23
Context Perception Parallel Decoder for Scene Text Recognition
Code
#4
CLIP4STR-L (DataComp-1B)
SOTA
91.4
Accuracy
· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
Code
#5
MGP-STR
SOTA
90.9
Accuracy
· Extra Data
· 2022-09-08
Multi-Granularity Prediction for Scene Text Recognition
Code
#6
CLIP4STR-L
90.8
Accuracy
· Extra Data
· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
Code
#7
CLIP4STR-B
90.6
Accuracy
· Extra Data
· 2023-05-23
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
Code
#8
SIGA_S
SOTA
87.6
Accuracy
· 2022-03-07
Self-supervised Implicit Glyph Attention for Text Recognition
Code
#9
S-GTR
SOTA
87.3
Accuracy
· Extra Data
· 2021-12-24
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Code
#10
MATRN
SOTA
86.6
Accuracy
· 2021-11-30
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Code
#11
CDistNet (Ours)
SOTA
86.25
Accuracy
· 2021-11-22
CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
Code
#12
DiffusionSTR
86
Accuracy
· 2023-06-29
DiffusionSTR: Diffusion Model for Scene Text Recognition
#13
DPAN
85.5
Accuracy
No paper
Code
#14
RCEED
SOTA
82.2
Accuracy
· 2021-06-13
Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
Code
#15
CSTR
SOTA
81.6
Accuracy
· 2021-02-22
Revisiting Classification Perspective on Scene Text Recognition
Code
#16
Yet Another Text Recognizer
80.2
Accuracy
· 2021-07-29
Why You Should Try the Real Data for the Scene Text Recognition
Code
#17
SEED
SOTA
80
Accuracy
· 2020-05-22
SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
Code
#18
TextScanner
SOTA
79.4
Accuracy
· 2019-12-28
TextScanner: Reading Characters in Order for Robust Scene Text Recognition
#19
SATRN
SOTA
79
Accuracy
· 2019-10-10
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
Code
#20
SAFL
77.5
Accuracy
· 2022-01-01
SAFL: A Self-Attention Scene Text Recognizer with Focal Loss
Code
#21
ASTER
76.1
Accuracy
No paper
Code
#22
DAN
74.5
Accuracy
· 2019-12-21
Decoupled Attention Network for Text Recognition
Code
#23
AON
SOTA
73
Accuracy
· 2017-11-12
AON: Towards Arbitrarily-Oriented Text Recognition
Code
#24
ViTSTR
72.6
Accuracy
· 2021-05-18
Vision Transformer for Fast and Efficient Scene Text Recognition
Code
#25
Baek et al.
71.8
Accuracy
· 2019-04-03
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
Code
#26
SAR
69.2
Accuracy
· 2018-11-02
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
Code