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

Unifying text detection and text recognition in an end-to-end trainingfashion has become a new trend for reading text in the wild, as these two tasksare highly relevant and complementary. In this paper, we investigate theproblem of scene text spotting, which aims at simultaneous text detection andrecognition in natural images. An end-to-end trainable neural network named asMask TextSpotter is presented. Different from the previous text spotters thatfollow the pipeline consisting of a proposal generation network and asequence-to-sequence recognition network, Mask TextSpotter enjoys a simple andsmooth end-to-end learning procedure, in which both detection and recognitioncan be achieved directly from two-dimensional space via semantic segmentation.Further, a spatial attention module is proposed to enhance the performance anduniversality. Benefiting from the proposed two-dimensional representation onboth detection and recognition, it easily handles text instances of irregularshapes, for instance, curved text. We evaluate it on four English datasets andone multi-language dataset, achieving consistently superior performance overstate-of-the-art methods in both detection and end-to-end text recognitiontasks. Moreover, we further investigate the recognition module of our methodseparately, which significantly outperforms state-of-the-art methods on bothregular and irregular text datasets for scene text recognition.

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes