📊 Showing 5 results | 📏 Metric: 1:1 Accuracy
| Rank | Model | Paper | 1:1 Accuracy | Date | Code |
|---|---|---|---|---|---|
| 1 | CLIP4STR-H (DFN-5B) | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 90.90 | 2023-05-23 | 📦 VamosC/CLIP4STR |
| 2 | CLIP4STR-L (DataComp-1B) 📚 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 90.60 | 2023-05-23 | 📦 VamosC/CLIP4STR |
| 3 | CLIP4STR-L 📚 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 88.80 | 2023-05-23 | 📦 VamosC/CLIP4STR |
| 4 | CLIP4STR-B 📚 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 87.00 | 2023-05-23 | 📦 VamosC/CLIP4STR |
| 5 | CCD-ViT-Base 📚 | Self-supervised Character-to-Character Distillation for Text Recognition | 86.00 | 2022-11-01 | 📦 tongkunguan/ccd |