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

Recently self-supervised representation learning has drawn considerableattention from the scene text recognition community. Different from previousstudies using contrastive learning, we tackle the issue from an alternativeperspective, i.e., by formulating the representation learning scheme in agenerative manner. Typically, the neighboring image patches among one text linetend to have similar styles, including the strokes, textures, colors, etc.Motivated by this common sense, we augment one image patch and use itsneighboring patch as guidance to recover itself. Specifically, we propose aSimilarity-Aware Normalization (SimAN) module to identify the differentpatterns and align the corresponding styles from the guiding patch. In thisway, the network gains representation capability for distinguishing complexpatterns such as messy strokes and cluttered backgrounds. Experiments show thatthe proposed SimAN significantly improves the representation quality andachieves promising performance. Moreover, we surprisingly find that ourself-supervised generative network has impressive potential for data synthesis,text image editing, and font interpolation, which suggests that the proposedSimAN has a wide range of practical applications.

SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization