| DTrOCR: Decoder-only Transformer for Optical Character Recognition | ✓ Link | 93.5 | DTrOCR 105M | 2023-08-30 |
| An Empirical Study of Scaling Law for OCR | ✓ Link | 92.6 | CLIP4STR-L* | 2023-12-29 |
| Context Perception Parallel Decoder for Scene Text Recognition | ✓ Link | 91.7 | CPPD | 2023-07-23 |
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 91.4 | CLIP4STR-L (DataComp-1B) | 2023-05-23 |
| Multi-Granularity Prediction for Scene Text Recognition | ✓ Link | 90.9 | MGP-STR | 2022-09-08 |
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 90.8 | CLIP4STR-L | 2023-05-23 |
| Decoder Pre-Training with only Text for Scene Text Recognition | ✓ Link | 90.8 | PARSeq + DPTR (real-data training) (extra data) | 2024-08-11 |
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 90.6 | CLIP4STR-B | 2023-05-23 |
| Scene Text Recognition with Permuted Autoregressive Sequence Models | ✓ Link | 89.6±0.3 | PARSeq | 2022-07-14 |
| Revisiting Scene Text Recognition: A Data Perspective | ✓ Link | 89.5 | MAERec-B (Union14M-U PT + Union14M-L FT) | 2023-07-17 |
| OTE: Exploring Accurate Scene Text Recognition Using One Token | ✓ Link | 89.1 | OTE A/SVTR | 2024-06-17 |
| Self-supervised Implicit Glyph Attention for Text Recognition | ✓ Link | 87.6 | SIGA_S | 2022-03-07 |
| Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition | ✓ Link | 87.3 | S-GTR | 2021-12-24 |
| TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition | | 87.1 | PARSeq + TEACH | 2025-08-02 |
| Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features | ✓ Link | 86.6 | MATRN | 2021-11-30 |
| TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition | ✓ Link | 86.5 | ABINet-LV + TPS++ | 2023-05-09 |
| CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition | ✓ Link | 86.25 | CDistNet (Ours) | 2021-11-22 |
| DiffusionSTR: Diffusion Model for Scene Text Recognition | | 86 | DiffusionSTR | 2023-06-29 |
| Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition | ✓ Link | 85.5 | DPAN | 2021-08-01 |
| TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition | | 84.8 | ViTSTR + TEACH | 2025-08-02 |
| TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models | ✓ Link | 84.1 | TrOCR Large (Syn+Benchmark) (extra data) | 2021-09-21 |
| IterVM: Iterative Vision Modeling Module for Scene Text Recognition | ✓ Link | 84.0 | IterNet (3× IterVM, 3× IterLM) (extra data) | 2022-04-06 |
| Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition | ✓ Link | 82.2 | RCEED | 2021-06-13 |
| Revisiting Classification Perspective on Scene Text Recognition | ✓ Link | 81.6 | CSTR | 2021-02-22 |
| Why You Should Try the Real Data for the Scene Text Recognition | ✓ Link | 80.2 | Yet Another Text Recognizer | 2021-07-29 |
| SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition | ✓ Link | 80 | SEED | 2020-05-22 |
| MASTER: Multi-Aspect Non-local Network for Scene Text Recognition | ✓ Link | 79.6 | MASTER (h=4, N=3) (extra data) | 2019-10-07 |
| TextScanner: Reading Characters in Order for Robust Scene Text Recognition | | 79.4 | TextScanner | 2019-12-28 |
| RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition | | 79.2 | RobustScanner (MJ + ST + real training) (extra data) | 2020-07-15 |
| On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention | ✓ Link | 79.0 | SATRN | 2019-10-10 |
| SAFL: A Self-Attention Scene Text Recognizer with Focal Loss | ✓ Link | 77.5 | SAFL | 2022-01-01 |
| ASTER: An Attentional Scene Text Recognizer with Flexible Rectification | ✓ Link | 76.1 | ASTER | 2018-06-25 |
| Decoupled Attention Network for Text Recognition | ✓ Link | 74.5 | DAN | 2019-12-21 |
| AON: Towards Arbitrarily-Oriented Text Recognition | ✓ Link | 73.0 | AON | 2017-11-12 |
| Data Augmentation for Scene Text Recognition | ✓ Link | 72.70 | TRBA + STRAug (extra data) | 2021-08-16 |
| Vision Transformer for Fast and Efficient Scene Text Recognition | ✓ Link | 72.6 | ViTSTR | 2021-05-18 |
| What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis | ✓ Link | 71.8 | Baek et al. | 2019-04-03 |
| Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition | ✓ Link | 69.2 | SAR | 2018-11-02 |