| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 91.9 | CLIP4STR-L (DataComp-1B, RBU 6.5M) | 2023-05-23 |
| Decoder Pre-Training with only Text for Scene Text Recognition | ✓ Link | 91.8 | PARSeq + DPTR (real-data training) (extra data) | 2024-08-11 |
| SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition | ✓ Link | 91.1 | SVTRv2-B | 2024-11-24 |
| Scene Text Recognition with Permuted Autoregressive Sequence Models | ✓ Link | 90.7 | PARSeq-S A (real data, 36-char) | 2022-07-14 |
| Platypus: A Generalized Specialist Model for Reading Text in Various Forms | ✓ Link | 90.7 | Platypus (extra data) | 2024-08-27 |
| Out of Length Text Recognition with Sub-String Matching | ✓ Link | 90.1 | SMTR (Union14M-L training) | 2024-07-17 |
| Context Perception Parallel Decoder for Scene Text Recognition | ✓ Link | 88.8 | NRTR-CPPD | 2023-07-23 |
| TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models | ✓ Link | 88.1 | TrOCR Large (Syn+Benchmark) (extra data) | 2021-09-21 |
| Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition | ✓ Link | 87.8 | CAM-Base | 2024-02-21 |
| IterVM: Iterative Vision Modeling Module for Scene Text Recognition | ✓ Link | 87.7 | IterNet (3× IterVM, 3× IterLM) (extra data) | 2022-04-06 |
| Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition | ✓ Link | 87.5 | LPV-Base (extra data) | 2023-05-09 |
| LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition | ✓ Link | 87.5 | LISTER-B (3-scale ensemble) | 2023-08-24 |
| Multi-Granularity Prediction for Scene Text Recognition | ✓ Link | 87.24 | MGP-STR Fuse Base (cumprod) | 2022-09-08 |
| SVTR: Scene Text Recognition with a Single Visual Model | ✓ Link | 86.6 | SVTR-L (Large) (extra data) | 2022-04-30 |
| CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition | ✓ Link | 86.0 | CDistNet (extra data) | 2021-11-22 |
| Towards Accurate Scene Text Recognition with Semantic Reasoning Networks | ✓ Link | 82.7 | SRN (extra data) | 2020-03-27 |
| SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition | ✓ Link | 80.0 | SE-ASTER (extra data) | 2020-05-22 |
| Data Augmentation for Scene Text Recognition | ✓ Link | 78.67 | TRBA + STRAug (extra data) | 2021-08-16 |
| Vision Transformer for Fast and Efficient Scene Text Recognition | ✓ Link | 78.5 | ViTSTR-Base + RandAugment (extra data) | 2021-05-18 |
| What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis | ✓ Link | 77.6 | TRBA (TPS-ResNet-BiLSTM-Attn) | 2019-04-03 |