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

Unsupervised pre-training on millions of digital-born or scanned documentshas shown promising advances in visual document understanding~(VDU). Whilevarious vision-language pre-training objectives are studied in existingsolutions, the document textline, as an intrinsic granularity in VDU, hasseldom been explored so far. A document textline usually contains words thatare spatially and semantically correlated, which can be easily obtained fromOCR engines. In this paper, we propose Wukong-Reader, trained with newpre-training objectives to leverage the structural knowledge nested in documenttextlines. We introduce textline-region contrastive learning to achievefine-grained alignment between the visual regions and texts of documenttextlines. Furthermore, masked region modeling and textline-grid matching arealso designed to enhance the visual and layout representations of textlines.Experiments show that our Wukong-Reader has superior performance on various VDUtasks such as information extraction. The fine-grained alignment over textlinesalso empowers Wukong-Reader with promising localization ability.

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding