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

Dominant scene text recognition models commonly contain two building blocks,a visual model for feature extraction and a sequence model for texttranscription. This hybrid architecture, although accurate, is complex and lessefficient. In this study, we propose a Single Visual model for Scene Textrecognition within the patch-wise image tokenization framework, which dispenseswith the sequential modeling entirely. The method, termed SVTR, firstlydecomposes an image text into small patches named character components.Afterward, hierarchical stages are recurrently carried out by component-levelmixing, merging and/or combining. Global and local mixing blocks are devised toperceive the inter-character and intra-character patterns, leading to amulti-grained character component perception. Thus, characters are recognizedby a simple linear prediction. Experimental results on both English and Chinesescene text recognition tasks demonstrate the effectiveness of SVTR. SVTR-L(Large) achieves highly competitive accuracy in English and outperformsexisting methods by a large margin in Chinese, while running faster. Inaddition, SVTR-T (Tiny) is an effective and much smaller model, which showsappealing speed at inference. The code is publicly available athttps://github.com/PaddlePaddle/PaddleOCR.

SVTR: Scene Text Recognition with a Single Visual Model