TextPerceptron

Reported on 4 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 Vision4 results

Text SpottingonSCUT-CTW1500
F-measure (%) - No Lexicon· 2020-02-17
57
best: 64.4 (A3S)
SOTA
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting arXiv:2002.06820
Text SpottingonICDAR 2015
F-measure (%) - Generic Lexicon· 2020-02-17
65.1
best: 80.3 (UNITS)
SOTA
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting arXiv:2002.06820
Text SpottingonICDAR 2015
F-measure (%) - Weak Lexicon· 2020-02-17
76.6
best: 84.1 (UNITS)
SOTA
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting arXiv:2002.06820
Text SpottingonICDAR 2015
F-measure (%) - Strong Lexicon· 2020-02-17
80.5
best: 89 (UNITS)
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting arXiv:2002.06820