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

Here we address a challenging problem: recognizing multiple text sequencesfrom an image by pure end-to-end learning. It is twofold: 1) Multiple textsequences recognition. Each image may contain multiple text sequences ofdifferent content, location and orientation, and we try to recognize all thetext sequences contained in the image. 2) Pure end-to-end (PEE) learning.Wesolve the problem in a pure end-to-end learning way where each training imageis labeled by only text transcripts of all contained sequences, without anygeometric annotations. Most existing works recognize multiple text sequencesfrom an image in a non-end-to-end (NEE) or quasi-end-to-end (QEE) way, in whicheach image is trained with both text transcripts and text locations.Onlyrecently, a PEE method was proposed to recognize text sequences from an imagewhere the text sequence was split to several lines in the image. However, itcannot be directly applied to recognizing multiple text sequences from animage. So in this paper, we propose a pure end-to-end learning method torecognize multiple text sequences from an image. Our method directly learnsmultiple sequences of probability distribution conditioned on each input image,and outputs multiple text transcripts with a well-designed decoding strategy.Toevaluate the proposed method, we constructed several datasets mainly based onan existing public dataset andtwo real application scenarios. Experimentalresults show that the proposed method can effectively recognize multiple textsequences from images, and outperforms CTC-based and attention-based baselinemethods.

Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image