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

Existing multi-style image captioning methods show promising results ingenerating a caption with accurate visual content and desired linguistic style.However, existing methods overlook the relationship between linguistic styleand visual content. To overcome this drawback, we propose style-awarecontrastive learning for multi-style image captioning. First, we present astyle-aware visual encoder with contrastive learning to mine potential visualcontent relevant to style. Moreover, we propose a style-aware triplet contrastobjective to distinguish whether the image, style and caption matched. Toprovide positive and negative samples for contrastive learning, we presentthree retrieval schemes: object-based retrieval, RoI-based retrieval andtriplet-based retrieval, and design a dynamic trade-off function to calculateretrieval scores. Experimental results demonstrate that our approach achievesstate-of-the-art performance. In addition, we conduct an extensive analysis toverify the effectiveness of our method.

Style-Aware Contrastive Learning for Multi-Style Image Captioning