Scene Text Recognition On Iiit5K
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| look-back-again-dual-parallel-attention | 96.2 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.5 |
| a-glyph-driven-topology-enhancement-network | 96.9 |
| multi-modal-text-recognition-networks | 96.6 |
| dtrocr-decoder-only-transformer-for-optical | 99.6 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.5 |
| multi-granularity-prediction-for-scene-text | 98.8 |
| scene-text-recognition-with-permuted | 99.1±0.1 |
| self-supervised-character-to-character | 98.0 |
| cdistnet-perceiving-multi-domain-character | 96.57 |
| self-supervised-character-to-character | 97.1 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.2 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.6 |
| self-supervised-character-to-character | 98.0 |
| visual-semantics-allow-for-textual-reasoning-1 | 97.5 |
| diffusionstr-diffusion-model-for-scene-text | 97.3 |
| context-perception-parallel-decoder-for-scene | 99.3 |