Scene Text Recognition on ICDAR 2003 (860)
96.9AccuracySIGAT
Evaluation Results
| Method | Links | |
|---|---|---|
| SIGATBackbone=ViT-B, Structure=Transformer, Size=32×1282022.03 | 96.9 | |
| SIGARBackbone=ResNet45, Structure=CNN, Size=32×1282022.03 | 96.5 | |
| PREN2DBackbone=EfficientNet-B3, Structure=CNN, Size=64×256, Venue=CVPR20212022.03 | 95.8 | |
| PlugNetBackbone=ResNet37, Structure=CNN, Size=32×100, Venue=ECCV20202022.03 | 95.7 | |
| PIMNetBackbone=ResNet50-FPN, Structure=CNN, Size=64×256, Venue=ACM MM20212022.03 | 95.2 | |
| TRBABackbone=ResNet31, Structure=CNN, Size=32×100, Venue=CVPR20212022.03 | 94.8 | |
| ViTSTRBackbone=ViT-B, Structure=Transformer, Size=224×224, Venue=ICDAR20212022.03 | 94.7 | |
| ABINetBackbone=ResNet45-Trns, Structure=Transformer, Size=32×128, Venue=CVPR20212022.03 | 94.3 |