English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Semantic information has been proved effective in scene text recognition.Most existing methods tend to couple both visual and semantic information in anattention-based decoder. As a result, the learning of semantic features isprone to have a bias on the limited vocabulary of the training set, which iscalled vocabulary reliance. In this paper, we propose a novel Visual-SemanticDecoupling Network (VSDN) to address the problem. Our VSDN contains a VisualDecoder (VD) and a Semantic Decoder (SD) to learn purer visual and semanticfeature representation respectively. Besides, a Semantic Encoder (SE) isdesigned to match SD, which can be pre-trained together by additionalinexpensive large vocabulary via a simple word correction task. Thus thesemantic feature is more unbiased and precise to guide the visual featurealignment and enrich the final character representation. Experiments show thatour method achieves state-of-the-art or competitive results on the standardbenchmarks, and outperforms the popular baseline by a large margin undercircumstances where the training set has a small size of vocabulary.

Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition