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

In this paper, we present StrucTexTv2, an effective document imagepre-training framework, by performing masked visual-textual prediction. Itconsists of two self-supervised pre-training tasks: masked image modeling andmasked language modeling, based on text region-level image masking. Theproposed method randomly masks some image regions according to the bounding boxcoordinates of text words. The objectives of our pre-training tasks arereconstructing the pixels of masked image regions and the corresponding maskedtokens simultaneously. Hence the pre-trained encoder can capture more textualsemantics in comparison to the masked image modeling that usually predicts themasked image patches. Compared to the masked multi-modal modeling methods fordocument image understanding that rely on both the image and text modalities,StrucTexTv2 models image-only input and potentially deals with more applicationscenarios free from OCR pre-processing. Extensive experiments on mainstreambenchmarks of document image understanding demonstrate the effectiveness ofStrucTexTv2. It achieves competitive or even new state-of-the-art performancein various downstream tasks such as image classification, layout analysis,table structure recognition, document OCR, and information extraction under theend-to-end scenario.

StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training