| Paper | Code | Scene LACC | Web LACC | Document LACC | Handwriting LACC | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|
| SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition | ✓ Link | 83.5 | 83.3 | 99.5 | 67.0 | SVTRv2-B | 2024-11-24 |
| Out of Length Text Recognition with Sub-String Matching | ✓ Link | 83.4 | 83.0 | 99.3 | 65.1 | SMTR (w/ training augmentation) | 2024-07-17 |
| Instruction-Guided Scene Text Recognition | ✓ Link | 82.0 | 81.7 | 99.5 | 63.8 | IGTR-AR-TS-Aug | 2024-01-31 |
| Decoder Pre-Training with only Text for Scene Text Recognition | ✓ Link | 80.0 | 79.6 | 98.9 | 64.4 | PARSeq + DPTR (BCTR training) (extra data) | 2024-08-11 |
| Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning | ✓ Link | 71.31 | 69.21 | 98.29 | 60.30 | CCR-CLIP (extra data) | 2023-09-03 |