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

Arbitrary shape text detection is a challenging task due to the high varietyand complexity of scenes texts. In this paper, we propose a novel unifiedrelational reasoning graph network for arbitrary shape text detection. In ourmethod, an innovative local graph bridges a text proposal model viaConvolutional Neural Network (CNN) and a deep relational reasoning network viaGraph Convolutional Network (GCN), making our network end-to-end trainable. Tobe concrete, every text instance will be divided into a series of smallrectangular components, and the geometry attributes (e.g., height, width, andorientation) of the small components will be estimated by our text proposalmodel. Given the geometry attributes, the local graph construction model canroughly establish linkages between different text components. For furtherreasoning and deducing the likelihood of linkages between the component and itsneighbors, we adopt a graph-based network to perform deep relational reasoningon local graphs. Experiments on public available datasets demonstrate thestate-of-the-art performance of our method.

Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection