| SRC-B-TextProcessingLab | 100.00% | 100.00% | 100.00% |
| Sogou_MM | 100.00% | 100.00% | 100.00% |
 Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 91.67% | 91.67% | 91.67% |
| Yunos_Robot1.0 | 83.33% | 100.00% | 90.91% |
| FOTS | 83.33% | 100.00% | 90.91% |
| e2e-mlt + bug fix | 83.33% | 100.00% | 90.91% |
| e2e-mlt | 91.67% | 84.62% | 88.00% |
| Megvii-Image++ | 83.33% | 90.91% | 86.96% |
| Sensetime V1 | 83.33% | 90.91% | 86.96% |
| HoText_v1 | 83.33% | 90.91% | 86.96% |
| SRC-B-MachineLearningLab | 83.33% | 90.91% | 86.96% |
| Smile | 83.33% | 90.91% | 86.96% |
| Tencent Youtu | 83.33% | 90.91% | 86.96% |
| Alibaba-PAI | 83.33% | 90.91% | 86.96% |
| CPN (multi-scale) | 83.33% | 90.91% | 86.96% |
| SRC-B-MachineLearningLab | 83.33% | 83.33% | 83.33% |
| Baidu IDL v3 | 83.33% | 83.33% | 83.33% |
| Baidu VIS | 83.33% | 83.33% | 83.33% |
| Baidu VIS v2 | 83.33% | 83.33% | 83.33% |
| Baidu VIS v2+ | 83.33% | 83.33% | 83.33% |
| TextProposals + DictNet | 83.33% | 76.92% | 80.00% |
| NVTextSpotter | 100.00% | 63.16% | 77.42% |
| M_FOTS_Orig | 75.00% | 75.00% | 75.00% |
| Baidu IDL | 75.00% | 50.00% | 60.00% |
| Char-level PTSD on SynthText | 58.33% | 41.18% | 48.28% |
| gts-swint-cocoonly-s4-3_1 | 58.33% | 41.18% | 48.28% |
| Baseline OpenCV3.0 + Tesseract | 33.33% | 57.14% | 42.11% |
| Deep2Text-MO | 16.67% | 22.22% | 19.05% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 8.33% | 100.00% | 15.38% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |