NVTextSpotter | 100.00% | 100.00% | 100.00% |
Alibaba-PAI | 100.00% | 93.75% | 96.77% |
Baidu VIS v2+ | 93.33% | 93.33% | 93.33% |
Tencent Youtu | 86.67% | 100.00% | 92.86% |
gts-swint-cocoonly-s4-3_1 | 86.67% | 92.86% | 89.66% |
Baidu VIS v2 | 86.67% | 86.67% | 86.67% |
Sensetime V1 | 80.00% | 85.71% | 82.76% |
Baidu VIS | 80.00% | 85.71% | 82.76% |
Baidu IDL v3 | 80.00% | 80.00% | 80.00% |
FOTS | 66.67% | 100.00% | 80.00% |
Smile | 80.00% | 80.00% | 80.00% |
SRC-B-MachineLearningLab | 73.33% | 84.62% | 78.57% |
e2e-mlt | 73.33% | 78.57% | 75.86% |
SRC-B-MachineLearningLab | 73.33% | 73.33% | 73.33% |
e2e-mlt + bug fix | 73.33% | 73.33% | 73.33% |
Sogou_MM | 46.67% | 70.00% | 56.00% |
TextProposals + DictNet | 40.00% | 85.71% | 54.55% |
HoText_v1 | 46.67% | 58.33% | 51.85% |
Yunos_Robot1.0 | 33.33% | 83.33% | 47.62% |
Baidu IDL | 46.67% | 38.89% | 42.42% |
M_FOTS_Orig | 40.00% | 40.00% | 40.00% |
Megvii-Image++ | 26.67% | 40.00% | 32.00% |
SRC-B-TextProcessingLab | 20.00% | 37.50% | 26.09% |
Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 6.67% | 25.00% | 10.53% |
Deep2Text-MO | 6.67% | 25.00% | 10.53% |
Char-level PTSD on SynthText | 6.67% | 25.00% | 10.53% |
Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
Beam search CUNI (decoding for TextSpotter - spell checked) | 0.00% | 0.00% | 0.00% |
Baseline OpenCV3.0 + Tesseract | 0.00% | 0.00% | 0.00% |