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/

Zendy Plus

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

Zendy Tools

Zendy Open

Scene Text Recognition (STR) is an important and challenging upstream taskfor building structured information databases, that involves recognizing textwithin images of natural scenes. Although current state-of-the-art (SOTA)models for STR exhibit high performance, they typically suffer from lowinference efficiency due to their reliance on hybrid architectures comprised ofvisual encoders and sequence decoders. In this work, we propose a VIsionPermutable extractor for fast and efficient Scene Text Recognition (SVIPTR),which achieves an impressive balance between high performance and rapidinference speeds in the domain of STR. Specifically, SVIPTR leverages avisual-semantic extractor with a pyramid structure, characterized by thePermutation and combination of local and global self-attention layers. Thisdesign results in a lightweight and efficient model and its inference isinsensitive to input length. Extensive experimental results on various standarddatasets for both Chinese and English scene text recognition validate thesuperiority of SVIPTR. Notably, the SVIPTR-T (Tiny) variant delivers highlycompetitive accuracy on par with other lightweight models and achieves SOTAinference speeds. Meanwhile, the SVIPTR-L (Large) attains SOTA accuracy insingle-encoder-type models, while maintaining a low parameter count andfavorable inference speed. Our proposed method provides a compelling solutionfor the STR challenge, which greatly benefits real-world applications requiringfast and efficient STR. The code is publicly available athttps://github.com/cxfyxl/VIPTR.

SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor