Text Spotting On Total Text
Metrics
F-measure (%) - Full Lexicon
F-measure (%) - No Lexicon
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | F-measure (%) - Full Lexicon | F-measure (%) - No Lexicon |
|---|---|---|
| glass-global-to-local-attention-for-scene | 83.0 | 76.6 |
| deepsolo-let-transformer-decoder-with | 89.6 | 83.6 |
| deepsolo-let-transformer-decoder-with | 87.0 | 79.7 |
| swintextspotter-scene-text-spotting-via | 84.1 | 74.3 |
| mango-a-mask-attention-guided-one-stage-scene | 83.6 | 72.9 |
| abcnet-v2-adaptive-bezier-curve-network-for | 78.1 | 70.4 |
| a3s-adversarial-learning-of-semantic | 85.1 | 79.4 |
| towards-unified-scene-text-spotting-based-on | 86.0 | 78.7 |
| deer-detection-agnostic-end-to-end-recognizer | 83.3 | 74.8 |
| mask-textspotter-v3-segmentation-proposal | 78.4 | 71.2 |
| deepsolo-let-transformer-decoder-with | 88.7 | 82.5 |
| text-spotting-transformers | 83.9 | 73.3 |