| scene-text-recognition-on-host | CCD-ViT-Base | #4 | 1:1 Accuracy: 77.3 |
| scene-text-recognition-on-icdar2013 | CCD-ViT-Base(ARD_2.8M) | #8 | Accuracy: 98.3 |
| scene-text-recognition-on-icdar2013 | CCD-ViT-Small(ARD_2.8M) | #9 | Accuracy: 98.3 |
| scene-text-recognition-on-icdar2013 | CCD-ViT-Tiny(ARD_2.8M) | #20 | Accuracy: 97.5 |
| scene-text-recognition-on-wost | CCD-ViT-Base | #8 | 1:1 Accuracy: 86.0 |
| scene-text-recognition-on-svtp | CCD-ViT-Base | #12 | Accuracy: 96.1 |
| scene-text-recognition-on-svtp | CCD-ViT-Small | #21 | Accuracy: 92.7 |
| scene-text-recognition-on-svtp | CCD-ViT-Tiny | #24 | Accuracy: 91.6 |
| scene-text-recognition-on-cute80 | CCD-ViT-Small(ARD_2.8M) | #17 | Accuracy: 98.3 |
| scene-text-recognition-on-cute80 | CCD-ViT-Base(ARD_2.8M) | #18 | Accuracy: 98.3 |
| scene-text-recognition-on-cute80 | CCD-ViT-Tiny(ARD_2.8M) | #21 | Accuracy: 95.8 |
| scene-text-recognition-on-svt | CCD-ViT-Base(ARD_2.8M) | #19 | Accuracy: 97.8 |
| scene-text-recognition-on-svt | CCD-ViT-Small(ARD_2.8M) | #22 | Accuracy: 96.4 |
| scene-text-recognition-on-svt | CCD-ViT-Tiny(ARD_2.8M) | #25 | Accuracy: 96.0 |
| scene-text-recognition-on-iiit5k | CCD-ViT-Small(ARD_2.8M) | #21 | Accuracy: 98.0 |
| scene-text-recognition-on-iiit5k | CCD-ViT-Base(ARD_2.8M) | #22 | Accuracy: 98.0 |
| scene-text-recognition-on-iiit5k | CCD-ViT-Tiny(ARD_2.8M) | #28 | Accuracy: 97.1 |