Scene Text Recognition On Cute80
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| clip4str-a-simple-baseline-for-scene-text-1 | 99.0 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.7 |
| dtrocr-decoder-only-transformer-for-optical | 99.1 |
| self-supervised-character-to-character | 98.3 |
| diffusionstr-diffusion-model-for-scene-text | 92.5 |
| visual-semantics-allow-for-textual-reasoning-1 | 94.7 |
| scene-text-recognition-with-permuted | 98.3±0.6 |
| multi-modal-text-recognition-networks | 93.5 |
| a-glyph-driven-topology-enhancement-network | 93.1 |
| cdistnet-perceiving-multi-domain-character | 89.58 |
| self-supervised-character-to-character | 98.3 |
| tps-attention-enhanced-thin-plate-spline-for | 92.4 |
| look-back-again-dual-parallel-attention | 91.9 |
| an-empirical-study-of-scaling-law-for-ocr | 99.65 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.3 |
| multi-granularity-prediction-for-scene-text | 99.31 |
| context-perception-parallel-decoder-for-scene | 99.7 |
| self-supervised-character-to-character | 95.8 |