Multiple attention encoded cascade R-CNN for scene text detection.

Yirui Wu Wenxiang Liu Shaohua Wan

Published in: J. Vis. Commun. Image Represent. (2021)

Keyphrases

text detection
urban scenes
outdoor scenes
multiple objects
video sequences
d scene
natural scene images
dynamic scenes
three dimensional
face recognition
object recognition
camera calibration
video analysis
urban environments
video images