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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Chinese characters have a huge set of character categories, more than 20,000and the number is still increasing as more and more novel characters continuebeing created. However, the enormous characters can be decomposed into acompact set of about 500 fundamental and structural radicals. This paperintroduces a novel radical analysis network (RAN) to recognize printed Chinesecharacters by identifying radicals and analyzing two-dimensional spatialstructures among them. The proposed RAN first extracts visual features frominput by employing convolutional neural networks as an encoder. Then a decoderbased on recurrent neural networks is employed, aiming at generating captionsof Chinese characters by detecting radicals and two-dimensional structuresthrough a spatial attention mechanism. The manner of treating a Chinesecharacter as a composition of radicals rather than a single character classlargely reduces the size of vocabulary and enables RAN to possess the abilityof recognizing unseen Chinese character classes, namely zero-shot learning.

Radical analysis network for zero-shot learning in printed Chinese character recognition