Scene Text Recognition on IC15 Cleaned (test)
94.1Word AccuracyCLIP4STR-B
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIP4STR-BTraining Data=3.3M real samples, Backbone=ViT-B2023.05 | 94.1 | |
| CLIP4STR-LTraining Data=3.3M real samples, Backbone=ViT-L2023.05 | 94 | |
| MPSTRTraining Data=3.3M real samples2023.05 | 93.9 | |
| PARSeqTraining Data=3.3M real samples2023.05 | 93.8 | |
| CLIP4STR-LTraining Data=3.3M real samples, Backbone=ViT-L2023.05 | 93.5 | |
| CLIP4STR-BTraining Data=3.3M real samples, Backbone=ViT-B2023.05 | 93.3 | |
| ABINetTraining Data=3.3M real samples2023.05 | 93.2 | |
| MPSTRTraining Data=3.3M real samples2023.05 | 92.7 | |
| PARSeqTraining Data=3.3M real samples2023.05 | 92.6 | |
| ABINetTraining Data=3.3M real samples2023.05 | 91.4 |