| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer | ✓ Link | 86.17 | E²STR-ICL | 2023-11-22 |
| Font-Agent: Enhancing Font Understanding with Large Language Models | 83.57 | Font-Agent (extra data) | 2025-06-11 | |
| Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing | 81.2 | DARLING (extra data) | 2024-05-07 | |
| Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition | ✓ Link | 75.7 | CFE-Base (synthetic training) (extra data) | 2024-07-08 |
| Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition | ✓ Link | 75.6 | CAM-Base | 2024-02-21 |