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

Training recognition models with synthetic images have achieved remarkableresults in text recognition. However, recognizing text from real-world imagesstill faces challenges due to the domain shift between synthetic and real-worldtext images. One of the strategies to eliminate the domain difference withoutmanual annotation is unsupervised domain adaptation (UDA). Due to thecharacteristic of sequential labeling tasks, most popular UDA methods cannot bedirectly applied to text recognition. To tackle this problem, we proposed a UDAmethod with minimizing latent entropy on sequence-to-sequence attention-basedmodels with classbalanced self-paced learning. Our experiments show that ourproposed framework achieves better recognition results than the existingmethods on most UDA text recognition benchmarks. All codes are publiclyavailable.

SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition