Sample RankingRecallPrecisionHmean
Baidu VIS v242.86%60.00%50.00%
Baidu VIS v2+42.86%50.00%46.15%
Sensetime V128.57%100.00%44.44%
Baidu VIS28.57%100.00%44.44%
SRC-B-MachineLearningLab28.57%100.00%44.44%
Alibaba-PAI28.57%100.00%44.44%
Tencent Youtu28.57%66.67%40.00%
NVTextSpotter42.86%37.50%40.00%
HoText_v128.57%50.00%36.36%
gts-swint-cocoonly-s4-3_128.57%40.00%33.33%
Sogou_MM28.57%33.33%30.77%
Yunos_Robot1.014.29%100.00%25.00%
FOTS14.29%100.00%25.00%
Baidu IDL14.29%50.00%22.22%
Baidu IDL v314.29%50.00%22.22%
SRC-B-MachineLearningLab14.29%33.33%20.00%
e2e-mlt + bug fix14.29%25.00%18.18%
Baseline-TextSpotter0.00%0.00%0.00%
Beam search CUNI +S (decoding for TextSpotter - no postprocessing)0.00%0.00%0.00%
Beam search CUNI (decoding for TextSpotter - spell checked)0.00%0.00%0.00%
Deep2Text-MO0.00%0.00%0.00%
Baseline OpenCV3.0 + Tesseract0.00%0.00%0.00%
Megvii-Image++0.00%0.00%0.00%
TextProposals + DictNet0.00%0.00%0.00%
SRC-B-TextProcessingLab0.00%0.00%0.00%
e2e-mlt0.00%0.00%0.00%
M_FOTS_Orig0.00%0.00%0.00%
Char-level PTSD on SynthText0.00%0.00%0.00%