Scene Text Recognition on CUTE Cleaned (test)
99.3Word AccuracyCLIP4STR-B
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIP4STR-BTraining Data=3.3M real samples, Backbone=ViT-B2023.05 | 99.3 | |
| MPSTRTraining Data=3.3M real samples2023.05 | 99 | |
| CLIP4STR-LTraining Data=3.3M real samples, Backbone=ViT-L2023.05 | 99 | |
| PARSeqTraining Data=3.3M real samples2023.05 | 98.6 | |
| ABINetTraining Data=3.3M real samples2023.05 | 97.2 |