Scene Text Recognition2020en

cute80

Dataset from Papers With Code

Metrics:accuracy, cer, wer, f1

Current State of the Art

CPPD

Unknown

99.7

accuracy

accuracy Progress Over Time

Showing 7 breakthroughs from Mar 2021 to May 2023

Key Milestones

Mar 2021

ABINet-LV

ABINet Language-Vision variant. CVPR 2021.

89.2

Source

Aug 2021

DPAN

From paper: Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition

91.9

+3.0%

Source

Nov 2021

MATRN

From paper: Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features

93.5

+1.7%

Source

Dec 2021

S-GTR

From paper: Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition

94.7

+1.3%

Source

Jul 2022

PARSeq

Lowercase alphanum eval. ECCV 2022.

98.6

+4.1%

Source

Sep 2022

MGP-STR

From paper: Multi-Granularity Prediction for Scene Text Recognition

99.3

+0.7%

Source

May 2023

CLIP4STR-L (DataComp-1B)Current SOTA

From paper: CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model

99.7

+0.4%

Source

Total Improvement

11.8%

Time Span

2y 2m

Breakthroughs

Current SOTA

99.7

Top Models Performance Comparison

Top 10 models ranked by accuracy

Best Score

99.7

Top Model

CPPD

Models Compared

Score Range

3.9

accuracyPrimary

#	Model	Score	Paper / Code	Date
1	CPPD	99.7	Context Perception Parallel Decoder for Scene Text Recognition Code	Jul 2023
2	CLIP4STR-L (DataComp-1B)	99.7	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code	May 2023
3	MGP-STR	99.31	Multi-Granularity Prediction for Scene Text Recognition Code	Sep 2022
4	CLIP4STR-B Research	99.3	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code	May 2023
5	DTrOCR 105M	99.1	DTrOCR: Decoder-only Transformer for Optical Character Recognition Code	Aug 2023
6	CLIP4STR-L	99	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model Code	May 2023
7	PARSeqOpen Source Research	98.61	Scene Text Recognition with Permuted Autoregressive Sequence Models	Jul 2022
8	CCD-ViT-Small(ARD_2.8M)	98.3	Self-supervised Character-to-Character Distillation for Text Recognition Code	Nov 2022
9	CCD-ViT-Base(ARD_2.8M)	98.3	Self-supervised Character-to-Character Distillation for Text Recognition Code	Nov 2022
10	CCD-ViT-Tiny(ARD_2.8M)	95.8	Self-supervised Character-to-Character Distillation for Text Recognition Code	Nov 2022
11	S-GTR	94.7	Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition Code	Dec 2021
12	MATRN Research	93.5	Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features Code	Nov 2021
13	SIGA_T	93.1	Self-supervised Implicit Glyph Attention for Text Recognition Code	Mar 2022
14	DiffusionSTR	92.5	DiffusionSTR: Diffusion Model for Scene Text Recognition	Jun 2023
15	NRTR+TPS++	92.4	TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition Code	May 2023
16	DPAN	91.9	Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text RecognitionCode	Aug 2021
17	CDistNet (Ours)	89.58	CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition Code	Nov 2021
18	ABINet-LVOpen Source Fang et al.	89.2	Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition	Mar 2021
19	TrOCR-large 558M	84.1	TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models	Sep 2021
20	TrOCR-base 334M	81.2	TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models	Sep 2021