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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Scene text recognition, as a cross-modal task involving vision and text, isan important research topic in computer vision. Most existing methods uselanguage models to extract semantic information for optimizing visualrecognition. However, the guidance of visual cues is ignored in the process ofsemantic mining, which limits the performance of the algorithm in recognizingirregular scene text. To tackle this issue, we propose a novel cross-modalfusion network (CMFN) for irregular scene text recognition, which incorporatesvisual cues into the semantic mining process. Specifically, CMFN consists of aposition self-enhanced encoder, a visual recognition branch and an iterativesemantic recognition branch. The position self-enhanced encoder providescharacter sequence position encoding for both the visual recognition branch andthe iterative semantic recognition branch. The visual recognition branchcarries out visual recognition based on the visual features extracted by CNNand the position encoding information provided by the position self-enhancedencoder. The iterative semantic recognition branch, which consists of alanguage recognition module and a cross-modal fusion gate, simulates the waythat human recognizes scene text and integrates cross-modal visual cues fortext recognition. The experiments demonstrate that the proposed CMFN algorithmachieves comparable performance to state-of-the-art algorithms, indicating itseffectiveness.

CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition