SAST detects arbitrarily-shaped scene text in a single forward pass by combining four geometric map predictions with point-to-quad pixel clustering, reaching 80.97 Hmean at 27.63 FPS on SCUT-CTW1500.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
SAST detects arbitrarily-shaped scene text in a single forward pass by combining four geometric map predictions with point-to-quad pixel clustering, reaching 80.97 Hmean at 27.63 FPS on SCUT-CTW1500.