Improved Fusion of Visual and Semantic Representations by Gated Co-Attention for Scene Text Recognition.

Junwei Zhou Xi Wang Jiao Dai Jizhong Han

Published in: ICCPR (2022)

Keyphrases

semantic representations
scene text recognition
natural language understanding
semantic representation
cross modal
visual information
semantic similarity
visual features
semantic space
high level
low level
semantic features
visual similarity
machine learning
natural language
expert systems