Representing word image using visual word embeddings and RNN for keyword spotting on historical document images

Hongxi Wei; Hui Zhang; Guanglai Gao

doi:10.1109/ICME.2017.8019403

Previous
Next
Table of Contents
Related Articles

2017 IEEE International Conference on Multimedia and Expo (ICME)

Representing word image using visual word embeddings and RNN for keyword spotting on historical document images

Year: 2017, Pages: 1368-1373

DOI Bookmark: 10.1109/ICME.2017.8019403

Authors

Hongxi Wei, School of Computer Science, Inner Mongolia University
Hui Zhang, School of Computer Science, Inner Mongolia University
Guanglai Gao, School of Computer Science, Inner Mongolia University

Representing word image using visual word embeddings and RNN for keyword spotting on historical document images

Authors

Abstract