ViTSTR-Transducer: Cross-Attention-Free Vision Transformer Transducer for Scene Text Recognition.

Rina Buoy Masakazu Iwamura Sovila Srun Koichi Kise

Published in: J. Imaging (2023)

Keyphrases

scene text recognition
vision system
real time
computer vision
case study
digital libraries
particle swarm optimization
data sets
neural network
decision making
image processing
image sequences
wide range
object recognition
fuzzy logic
visual attention