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

Recently, Transformer-based text detection techniques have sought to predictpolygons by encoding the coordinates of individual boundary vertices usingdistinct query features. However, this approach incurs a significant memoryoverhead and struggles to effectively capture the intricate relationshipsbetween vertices belonging to the same instance. Consequently, irregular textlayouts often lead to the prediction of outlined vertices, diminishing thequality of results. To address these challenges, we present an innovativeapproach rooted in Sparse R-CNN: a cascade decoding pipeline for polygonprediction. Our method ensures precision by iteratively refining polygonpredictions, considering both the scale and location of preceding results.Leveraging this stabilized regression pipeline, even employing just a singlefeature vector to guide polygon instance regression yields promising detectionresults. Simultaneously, the leverage of instance-level feature proposalsubstantially enhances memory efficiency (>50% less vs. the state-of-the-artmethod DPText-DETR) and reduces inference speed (>40% less vs. DPText-DETR)with minor performance drop on benchmarks.

Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text