| Paper | Code | 1:1 Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | ✓ Link | 81.9 | CLIP4STR-L | 2023-05-23 |
| Multi-Granularity Prediction for Scene Text Recognition | ✓ Link | 81.7 | MGP-STR | 2022-09-08 |
| Decoder Pre-Training with only Text for Scene Text Recognition | ✓ Link | 81.3 | 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 | 81.1 | CLIP4STR-B | 2023-05-23 |
| Scene Text Recognition with Permuted Autoregressive Sequence Models | ✓ Link | 79.8±0.1 | PARSeq | 2022-07-14 |
| Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer | ✓ Link | 78.38 | E²STR-ICL | 2023-11-22 |
| LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition | ✓ Link | 78.0 | LISTER-Bh | 2023-08-24 |
| Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition | ✓ Link | 66.3 | CFE-Base (synthetic training) (extra data) | 2024-07-08 |