Scene Text Recognition On Svt
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Accuracy |
|---|---|
| clip4str-a-simple-baseline-for-scene-text-1 | 98.5 |
| cdistnet-perceiving-multi-domain-character | 93.82 |
| robust-scene-text-recognition-with-automatic | 81.9 |
| a-glyph-driven-topology-enhancement-network | 95.1 |
| cstr-a-classification-perspective-on-scene | 90.6 |
| clip4str-a-simple-baseline-for-scene-text-1 | 98.3 |
| clip4str-a-simple-baseline-for-scene-text-1 | 99.1 |
| multi-modal-text-recognition-networks | 95 |
| seed-semantics-enhanced-encoder-decoder | 89.6 |
| self-supervised-character-to-character | 97.8 |
| self-supervised-character-to-character | 96.4 |
| diffusionstr-diffusion-model-for-scene-text | 93.6 |
| representation-and-correlation-enhanced | 91.8 |
| visual-semantics-allow-for-textual-reasoning-1 | 95.8 |
| towards-accurate-scene-text-recognition-with | 91.5 |
| look-back-again-dual-parallel-attention | 93.9 |
| clip4str-a-simple-baseline-for-scene-text-1 | 98.6 |
| tps-attention-enhanced-thin-plate-spline-for | 94.6 |
| star-net-a-spatial-attention-residue-network | 83.6 |
| an-empirical-study-of-scaling-law-for-ocr | 98.76 |
| scene-text-recognition-from-two-dimensional | 86.4 |
| dtrocr-decoder-only-transformer-for-optical | 98.9 |
| what-is-wrong-with-scene-text-recognition | 87.5 |
| multi-granularity-prediction-for-scene-text | 98.6 |
| self-supervised-character-to-character | 96.0 |
| synthetic-data-and-artificial-neural-networks | 68.0 |
| context-perception-parallel-decoder-for-scene | 98.5 |
| scene-text-recognition-with-permuted | 97.9±0.2 |
| on-recognizing-texts-of-arbitrary-shapes-with | 91.3 |
| why-you-should-try-the-real-data-for-the | 94.7 |
| textscanner-reading-characters-in-order-for | 90.1 |
| aster-an-attentional-scene-text-recognizer | 89.5 |
| vision-transformer-for-fast-and-efficient | 87.7 |
| an-end-to-end-trainable-neural-network-for | 80.8 |
| safl-a-self-attention-scene-text-recognizer-1 | 88.6 |
| show-attend-and-read-a-simple-and-strong | 84.5 |
| decoupled-attention-network-for-text | 89.2 |