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

Document images are a ubiquitous source of data where the text is organizedin a complex hierarchical structure ranging from fine granularity (e.g.,words), medium granularity (e.g., regions such as paragraphs or figures), tocoarse granularity (e.g., the whole page). The spatial hierarchicalrelationships between content at different levels of granularity are crucialfor document image understanding tasks. Existing methods learn features fromeither word-level or region-level but fail to consider both simultaneously.Word-level models are restricted by the fact that they originate from pure-textlanguage models, which only encode the word-level context. In contrast,region-level models attempt to encode regions corresponding to paragraphs ortext blocks into a single embedding, but they perform worse with additionalword-level features. To deal with these issues, we propose MGDoc, a newmulti-modal multi-granular pre-training framework that encodes page-level,region-level, and word-level information at the same time. MGDoc uses a unifiedtext-visual encoder to obtain multi-modal features across differentgranularities, which makes it possible to project the multi-granular featuresinto the same hyperspace. To model the region-word correlation, we design across-granular attention mechanism and specific pre-training tasks for ourmodel to reinforce the model of learning the hierarchy between regions andwords. Experiments demonstrate that our proposed model can learn betterfeatures that perform well across granularities and lead to improvements indownstream tasks.

MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding