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

Visual information extraction (VIE) has attracted considerable attentionrecently owing to its various advanced applications such as documentunderstanding, automatic marking and intelligent education. Most existing worksdecoupled this problem into several independent sub-tasks of text spotting(text detection and recognition) and information extraction, which completelyignored the high correlation among them during optimization. In this paper, wepropose a robust visual information extraction system (VIES) towards real-worldscenarios, which is a unified end-to-end trainable framework for simultaneoustext detection, recognition and information extraction by taking a singledocument image as input and outputting the structured information.Specifically, the information extraction branch collects abundant visual andsemantic representations from text spotting for multimodal feature fusion andconversely, provides higher-level semantic clues to contribute to theoptimization of text spotting. Moreover, regarding the shortage of publicbenchmarks, we construct a fully-annotated dataset called EPHOIE(https://github.com/HCIILAB/EPHOIE), which is the first Chinese benchmark forboth text spotting and visual information extraction. EPHOIE consists of 1,494images of examination paper head with complex layouts and background, includinga total of 15,771 Chinese handwritten or printed text instances. Compared withthe state-of-the-art methods, our VIES shows significant superior performanceon the EPHOIE dataset and achieves a 9.01% F-score gain on the widely usedSROIE dataset under the end-to-end scenario.

Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution