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

The generation of Chinese fonts has a wide range of applications. Thecurrently predominated methods are mainly based on deep generative models,especially the generative adversarial networks (GANs). However, existingGAN-based models usually suffer from the well-known mode collapse problem. Whenmode collapse happens, the kind of GAN-based models will be failure to yieldthe correct fonts. To address this issue, we introduce a one-bit strokeencoding and a few-shot semi-supervised scheme (i.e., using a few paired dataas semi-supervised information) to explore the local and global structureinformation of Chinese characters respectively, motivated by the intuition thatstrokes and characters directly embody certain local and global modes ofChinese characters. Based on these ideas, this paper proposes an effectivemodel called \textit{StrokeGAN+}, which incorporates the stroke encoding andthe few-shot semi-supervised scheme into the CycleGAN model. The effectivenessof the proposed model is demonstrated by amounts of experiments. Experimentalresults show that the mode collapse issue can be effectively alleviated by theintroduced one-bit stroke encoding and few-shot semi-supervised trainingscheme, and that the proposed model outperforms the state-of-the-art models infourteen font generation tasks in terms of four important evaluation metricsand the quality of generated characters. Besides CycleGAN, we also show thatthe proposed idea can be adapted to other existing models to improve theirperformance. The effectiveness of the proposed model for the zero-shottraditional Chinese font generation is also evaluated in this paper.

StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding