Scene Text Recognition on WordArt
88.55AccuracyWATERec
Evaluation Results
| Method | Links | |
|---|---|---|
| WATERecType=AR2026.06 | 88.55 | |
| SVTRv2-ARType=AR2026.06 | 87.36 | |
| SVTRv2Type=CTC2026.06 | 86.56 | |
| MAERecType=AR2026.06 | 86.23 | |
| ViSuDatasets=RL+RU2024.11 | 85.9 | |
| ABINetType=PD2026.06 | 84.64 | |
| PARSeqType=AR2026.06 | 84.51 | |
| OTEType=AR2026.06 | 83.98 | |
| CLIP-OCR†Datasets=RL2024.11 | 83.5 | |
| ParSeq†Datasets=RL2024.11 | 83.1 | |
| TRBA-cr†Datasets=RL+RU2024.11 | 82.7 | |
| LPV†Datasets=RL2024.11 | 82.5 | |
| CPPDType=PD2026.06 | 81.6 | |
| BUSNetType=PD2026.06 | 80.67 | |
| MGP†Datasets=RL2024.11 | 80.5 | |
| Baseline-ViSuTraining Datasets=SL+RU2024.11 | 80.5 | |
| LPVType=PD2026.06 | 80.34 | |
| TRBA-cr*Training Datasets=SL+RU22024.11 | 80.2 | |
| TRBA-ViSuTraining Datasets=SL+RU2024.11 | 77.7 | |
| SVTRType=CTC2026.06 | 76.96 | |
| TRBA-cr†Training Datasets=SL+RU2024.11 | 76.7 | |
| LISTER†Datasets=RL2024.11 | 74.8 | |
| CLIP-OCRTraining Datasets=SL2024.11 | 73.9 | |
| MGP*Training Datasets=SL2024.11 | 72.4 | |
| BaselineTraining Datasets=SL2024.11 | 72.3 | |
| ABINet*Training Datasets=SL+Wiki+Uber2024.11 | 71.3 | |
| CornerTransformerTraining Datasets=SL2024.11 | 70.8 | |
| LISTER*Training Datasets=SL2024.11 | 69.8 | |
| TRBA†Training Datasets=SL2024.11 | 69.5 | |
| TRBA-pr*Datasets=RL1+RU12024.11 | 64.3 | |
| TRBA-pr*Training Datasets=RL+RU12024.11 | 64.3 | |
| CRNNType=CTC2026.06 | 62.54 | |
| CRNN-ViSuTraining Datasets=SL+RU2024.11 | 56.3 | |
| CRNN†Training Datasets=SL2024.11 | 54 | |
| CRNN-pr*Datasets=RL1+RU12024.11 | 53.4 | |
| CRNN-pr*Training Datasets=RL+RU12024.11 | 53.4 |