Scene Text Recognition On Host
평가 지표
1:1 Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | 1:1 Accuracy | Paper Title | Repository |
|---|---|---|---|
| CLIP4STR-B | 79.8 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | - |
| CCD-ViT-Base | 77.3 | Self-supervised Character-to-Character Distillation for Text Recognition | - |
| CLIP4STR-L | 82.7 | CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | - |
0 of 3 row(s) selected.