📊 Showing 3 results | 📏 Metric: 1:1 Accuracy
| Rank | Model | Paper | 1:1 Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | CLIP4STR-L 📚 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 82.70 | 2023-05-23 | 📦 VamosC/CLIP4STR |
| 2 | CLIP4STR-B 📚 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 79.80 | 2023-05-23 | 📦 VamosC/CLIP4STR |
| 3 | CCD-ViT-Base 📚 | Self-supervised Character-to-Character Distillation for Text Recognition | 77.30 | 2022-11-01 | 📦 tongkunguan/ccd |