GLASS: Global to Local Attention for Scene-Text Spotting
Open paper
Benchmark
Model
Rank
Results
text-spotting-on-total-text
GLASS
#7
F-measure (%) - No Lexicon: 76.6
F-measure (%) - Full Lexicon: 83.0
text-spotting-on-icdar-2015
GLASS
#9
F-measure (%) - Strong Lexicon: 84.7
F-measure (%) - Weak Lexicon: 80.1
…
Rank counts only results with a code link.