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

End-to-end text spotting is a vital computer vision task that aims tointegrate scene text detection and recognition into a unified framework.Typical methods heavily rely on Region-of-Interest (RoI) operations to extractlocal features and complex post-processing steps to produce final predictions.To address these limitations, we propose TextFormer, a query-based end-to-endtext spotter with Transformer architecture. Specifically, using query embeddingper text instance, TextFormer builds upon an image encoder and a text decoderto learn a joint semantic understanding for multi-task modeling. It allows formutual training and optimization of classification, segmentation, andrecognition branches, resulting in deeper feature sharing without sacrificingflexibility or simplicity. Additionally, we design an Adaptive GlobalaGgregation (AGG) module to transfer global features into sequential featuresfor reading arbitrarily-shaped texts, which overcomes the sub-optimizationproblem of RoI operations. Furthermore, potential corpus information isutilized from weak annotations to full labels through mixed supervision,further improving text detection and end-to-end text spotting results.Extensive experiments on various bilingual (i.e., English and Chinese)benchmarks demonstrate the superiority of our method. Especially on TDA-ReCTSdataset, TextFormer surpasses the state-of-the-art method in terms of 1-NED by13.2%.

TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision