OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold.

Mohamed Yousef Tom E. Bishop

Published in: CVPR (2020)

Keyphrases

weakly supervised
learning algorithm
topic models
text recognition
image segmentation
object class
semi supervised
supervised learning
higher order
superpixels
image regions
segmentation algorithm
level set
object detection
active learning
reinforcement learning
web pages