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

Scene text recognition (STR) attracts much attention over the years becauseof its wide application. Most methods train STR model in a fully supervisedmanner which requires large amounts of labeled data. Although synthetic datacontributes a lot to STR, it suffers from the real-tosynthetic domain gap thatrestricts model performance. In this work, we aim to boost STR models byleveraging both synthetic data and the numerous real unlabeled images,exempting human annotation cost thoroughly. A robust consistency regularizationbased semi-supervised framework is proposed for STR, which can effectivelysolve the instability issue due to domain inconsistency between synthetic andreal images. A character-level consistency regularization is designed tomitigate the misalignment between characters in sequence recognition. Extensiveexperiments on standard text recognition benchmarks demonstrate theeffectiveness of the proposed method. It can steadily improve existing STRmodels, and boost an STR model to achieve new state-of-the-art results. To ourbest knowledge, this is the first consistency regularization based frameworkthat applies successfully to STR.

Pushing the Performance Limit of Scene Text Recognizer without Human Annotation