Reading Scene Text by Fusing Visual Attention with Semantic Representations.

Zhiguang Liu Liangwei Wang Jian Qiao

Published in: ICMR (2021)

Keyphrases

visual attention
scene text
semantic representations
natural scene images
text detection
natural scenes
eye tracking
text regions
saliency map
eye movements
vision system
semantic similarity
higher level
video frames
object recognition
semantic features
video analysis
semantic concepts
multi modal