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 5 breakthroughs from Aug 2021 to May 2023
Key Milestones
Aug 2021
DPAN
From paper: Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
91.9
Nov 2021
MATRN
From paper: Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
93.5
+1.7%
Dec 2021
S-GTR
From paper: Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
94.7
+1.3%
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%
Total Improvement
8.5%
Time Span
1y 9m
Breakthroughs
5
Current SOTA
99.7
Top Models Performance Comparison
Top 10 models ranked by accuracy
Best Score
99.7
Top Model
CPPD
Models Compared
10
Score Range
5.0
accuracyPrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | CPPD | 99.7 | Jul 2023 | |
| 2 | CLIP4STR-L (DataComp-1B) | 99.7 | May 2023 | |
| 3 | MGP-STR | 99.31 | Sep 2022 | |
| 4 | CLIP4STR-B* | 99.3 | May 2023 | |
| 5 | DTrOCR 105M | 99.1 | Aug 2023 | |
| 6 | CLIP4STR-L | 99 | May 2023 | |
| 7 | CCD-ViT-Small(ARD_2.8M) | 98.3 | Nov 2022 | |
| 8 | CCD-ViT-Base(ARD_2.8M) | 98.3 | Nov 2022 | |
| 9 | CCD-ViT-Tiny(ARD_2.8M) | 95.8 | Nov 2022 | |
| 10 | S-GTR | 94.7 | Dec 2021 | |
| 11 | MATRN | 93.5 | Nov 2021 | |
| 12 | SIGA_T | 93.1 | Mar 2022 | |
| 13 | DiffusionSTR | 92.5 | Jun 2023 | |
| 14 | NRTR+TPS++ | 92.4 | May 2023 | |
| 15 | DPAN | 91.9 | Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text RecognitionCode | Aug 2021 |
| 16 | CDistNet (Ours) | 89.58 | Nov 2021 |
Related Papers11
DTrOCR: Decoder-only Transformer for Optical Character Recognition
Aug 2023Models: DTrOCR 105M
Context Perception Parallel Decoder for Scene Text Recognition
Jul 2023Models: CPPD
DiffusionSTR: Diffusion Model for Scene Text Recognition
Jun 2023Models: DiffusionSTR
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model
May 2023Models: CLIP4STR-L (DataComp-1B), CLIP4STR-B*, CLIP4STR-L
TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition
May 2023Models: NRTR+TPS++
Self-supervised Character-to-Character Distillation for Text Recognition
Nov 2022Models: CCD-ViT-Small(ARD_2.8M), CCD-ViT-Base(ARD_2.8M), CCD-ViT-Tiny(ARD_2.8M)
Multi-Granularity Prediction for Scene Text Recognition
Sep 2022Models: MGP-STR
Self-supervised Implicit Glyph Attention for Text Recognition
Mar 2022Models: SIGA_T
CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
Nov 2021Models: CDistNet (Ours)