| gts-swint-cocoonly-s4-3_1 | 100.00% | 100.00% | 100.00% |
| CPN (multi-scale) | 91.67% | 100.00% | 95.65% |
| Sensetime V1 | 91.67% | 91.67% | 91.67% |
| Baidu VIS v2+ | 91.67% | 91.67% | 91.67% |
| Alibaba-PAI | 91.67% | 91.67% | 91.67% |
| NVTextSpotter | 91.67% | 91.67% | 91.67% |
| Sogou_MM | 83.33% | 90.91% | 86.96% |
| HoText_v1 | 83.33% | 83.33% | 83.33% |
| FOTS | 75.00% | 90.00% | 81.82% |
| Baidu VIS | 75.00% | 81.82% | 78.26% |
| Yunos_Robot1.0 | 66.67% | 88.89% | 76.19% |
| Tencent Youtu | 66.67% | 88.89% | 76.19% |
| Baidu IDL v3 | 75.00% | 75.00% | 75.00% |
| Baidu VIS v2 | 75.00% | 75.00% | 75.00% |
| Smile | 75.00% | 75.00% | 75.00% |
| SRC-B-MachineLearningLab | 66.67% | 80.00% | 72.73% |
| e2e-mlt | 66.67% | 72.73% | 69.57% |
| SRC-B-MachineLearningLab | 58.33% | 70.00% | 63.64% |
| M_FOTS_Orig | 58.33% | 70.00% | 63.64% |
| e2e-mlt + bug fix | 58.33% | 58.33% | 58.33% |
| TextProposals + DictNet | 41.67% | 83.33% | 55.56% |
| Megvii-Image++ | 50.00% | 60.00% | 54.55% |
 Deep2Text-MO | 33.33% | 57.14% | 42.11% |
| Baidu IDL | 33.33% | 50.00% | 40.00% |
| SRC-B-TextProcessingLab | 25.00% | 37.50% | 30.00% |
| Baseline OpenCV3.0 + Tesseract | 16.67% | 100.00% | 28.57% |
| Char-level PTSD on SynthText | 16.67% | 22.22% | 19.05% |
| Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 8.33% | 16.67% | 11.11% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 0.00% | 0.00% | 0.00% |