| Paper | Code | 1:1 Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 82.7 | CLIP4STR-L | 2023-05-23 |
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 79.8 | CLIP4STR-B | 2023-05-23 |
| Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition | ✓ Link | 78.6 | CAM-Tiny | 2024-02-21 |
| Self-supervised Character-to-Character Distillation for Text Recognition | ✓ Link | 77.3 | CCD-ViT-Base | 2022-11-01 |
| Font-Agent: Enhancing Font Understanding with Large Language Models | 76.54 | Font-Agent (extra data) | 2025-06-11 | |
| SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition | ✓ Link | 73.8 | SVTRv2-B | 2024-11-24 |
| Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing | 70.8 | DARLING (extra data) | 2024-05-07 | |
| From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network | ✓ Link | 50.3 | VisionLAN (extra data) | 2021-08-22 |