EAST + VGG16

Reported on 3 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 Vision3 results

Scene Text DetectiononCOCO-Text
F-Measure· 2017-04-11
39.45
best: 59.1 (Corner-based Region Proposals)
SOTA
EAST: An Efficient and Accurate Scene Text Detector arXiv:1704.03155
Scene Text DetectiononCOCO-Text
Precision· 2017-04-11
50.39
best: 60.87 (TextBoxes++_MS)
SOTA
EAST: An Efficient and Accurate Scene Text Detector arXiv:1704.03155
Scene Text DetectiononCOCO-Text
Recall· 2017-04-11
32.4
best: 63.3 (Corner-based Region Proposals)
SOTA
EAST: An Efficient and Accurate Scene Text Detector arXiv:1704.03155