Scene Text Recognition on ICDAR 2013
97.8AccuracySIGAT
Evaluation Results
| Method | Links | |
|---|---|---|
| SIGATBackbone=ViT-B, Structure=Transformer, Size=32×1282022.03 | 97.8 | |
| MGP-STRBackbone=ViT-B, Structure=Transformer, Size=32×128, Venue=ECCV20222022.03 | 97.3 | |
| SVTRBackbone=SVTR-L, Structure=Transformer*, Size=48×160, Venue=IJCAI20222022.03 | 97.2 | |
| SIGARBackbone=ResNet45, Structure=CNN, Size=32×1282022.03 | 97 | |
| SIGAsBackbone=SVTR-L, Structure=Transformer*, Size=48×1602022.03 | 97 | |
| SIGATBackbone=ViT-B, Structure=Transformer, Size=32×1282022.03 | 96.8 | |
| PREN2DBackbone=EfficientNet-B3, Structure=CNN, Size=64×256, Venue=CVPR20212022.03 | 96.4 | |
| Corner TransformerBackbone=SATRN, Structure=Transformer, Size=32×128, Venue=ECCV20222022.03 | 96.4 | |
| LevOCRBackbone=ViT, Structure=Transformer, Size=32×128, Venue=ECCV20222022.03 | 95.9 | |
| SIGARBackbone=ResNet45, Structure=CNN, Size=32×1282022.03 | 95.6 | |
| TRBABackbone=ResNet31, Structure=CNN, Size=32×100, Venue=CVPR20212022.03 | 95.1 | |
| LevOCRBackbone=ResNet45, Structure=CNN, Size=32×128, Venue=ECCV20222022.03 | 95.1 | |
| SGBANetBackbone=ResNet45-FPN, Structure=CNN, Size=64×256, Venue=ECCV20222022.03 | 95.1 | |
| PlugNetBackbone=ResNet37, Structure=CNN, Size=32×100, Venue=ECCV20202022.03 | 95 | |
| ABINet+ConCLR+Backbone=ResNet45-Trns, Structure=Transformer, Size=32×128, Venue=AAAI20222022.03 | 94.9 | |
| S-GTR+Backbone=ResNet50Dilated-PPM, Structure=CNN, Size=64×256, Venue=AAAI20222022.03 | 94.8 | |
| ABINetBackbone=ResNet45-Trns, Structure=Transformer, Size=32×128, Venue=CVPR20212022.03 | 94.7 | |
| DANBackbone=ResNet45, Structure=CNN, Size=32×128, Venue=AAAI20202022.03 | 93.9 | |
| TRBABackbone=ResNet31, Structure=CNN, Size=32×100, Venue=CVPR20212022.03 | 93.9 | |
| PIMNetBackbone=ResNet50-FPN, Structure=CNN, Size=64×256, Venue=ACM MM20212022.03 | 93.4 | |
| Text is TextBackbone=ResNet31, Structure=CNN, Size=48×160, Venue=ICCV20212022.03 | 93.3 | |
| SRNBackbone=ResNet50-FPN, Structure=CNN, Size=64×256, Venue=CVPR20202022.03 | 93.2 | |
| ViTSTRBackbone=ViT-B, Structure=Transformer, Size=224×224, Venue=ICDAR20212022.03 | 93.2 | |
| ABINetBackbone=ResNet45-Trns, Structure=Transformer, Size=32×128, Venue=CVPR20212022.03 | 93.2 | |
| TextScannerBackbone=ResNet50, Structure=CNN, Size=64×256, Venue=AAAI20202022.03 | 92.9 | |
| ViTSTRBackbone=ViT-B, Structure=Transformer, Size=224×224, Venue=ICDAR20212022.03 | 92.4 | |
| CA-FCNBackbone=VGG16, Structure=CNN, Size=64×256, Venue=AAAI20192022.03 | 91.5 | |
| DeepSoloBackbone=ViTAEv2-S2025.03 | 89.7 | |
| DeepSoloBackbone=ResNet-502025.03 | 88.8 | |
| MANGO2025.03 | 88.7 | |
| SPTS2025.03 | 88.5 | |
| TESTR2025.03 | 86.4 | |
| MaskTextSpotter2025.03 | 84.1 |