Scene Text Recognition On Svtp
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| clip4str-a-simple-baseline-for-scene-text-1 | 97.4 |
| look-back-again-dual-parallel-attention | 89.0 |
| clip4str-a-simple-baseline-for-scene-text-1 | 97.2 |
| clip4str-a-simple-baseline-for-scene-text-1 | 98.1 |
| a-glyph-driven-topology-enhancement-network | 90.5 |
| multi-modal-text-recognition-networks | 90.6 |
| self-supervised-character-to-character | 96.1 |
| self-supervised-character-to-character | 92.7 |
| self-supervised-character-to-character | 91.6 |
| dtrocr-decoder-only-transformer-for-optical | 98.6 |
| cdistnet-perceiving-multi-domain-character | 89.77 |
| scene-text-recognition-with-permuted | 95.7±0.9 |
| context-perception-parallel-decoder-for-scene | 96.7 |
| diffusionstr-diffusion-model-for-scene-text | 89.2 |
| an-empirical-study-of-scaling-law-for-ocr | 98.13 |
| visual-semantics-allow-for-textual-reasoning-1 | 90.6 |
| multi-granularity-prediction-for-scene-text | 98.3 |