Label Embedding: A Frugal Baseline for Text Recognition.

José A. Rodríguez-Serrano Albert Gordo Florent Perronnin

Published in: Int. J. Comput. Vis. (2015)

Keyphrases

text recognition
viterbi algorithm
optical character recognition
hidden markov models
multi label
vector space
markov model
video sequences
vision system
saliency map