CharNet H-88 (multi-scale)

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision5 results

Scene Text DetectiononTotal-Text
Recall· 2019-10-17
85
best: 88.1 (MixNet)
SOTA
Convolutional Character Networks arXiv:1910.07954
Scene Text DetectiononICDAR 2015
F-Measure· 2019-10-17
91.55
best: 92.23 (TextFuseNet (ResNeXt-101))
SOTA
Convolutional Character Networks arXiv:1910.07954
Scene Text DetectiononICDAR 2015
Precision· 2019-10-17
92.65
best: 93.96 (TextFuseNet (ResNeXt-101))
SOTA
Convolutional Character Networks arXiv:1910.07954
Scene Text DetectiononTotal-Text
Precision· 2019-10-17
88
best: 93 (MixNet)
Convolutional Character Networks arXiv:1910.07954
Scene Text DetectiononICDAR 2015
Recall· 2019-10-17
90.47
best: 91.98 (CharNet H-88 (single-scale))
Convolutional Character Networks arXiv:1910.07954