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

Generating images with conditional descriptions gains increasing interests inrecent years. However, existing conditional inputs are suffering from eitherunstructured forms (captions) or limited information and expensive labeling(scene graphs). For a targeted scene, the core items, objects, are usuallydefinite while their interactions are flexible and hard to clearly define.Thus, we introduce a more rational setting, generating a realistic image fromthe objects and captions. Under this setting, objects explicitly define thecritical roles in the targeted images and captions implicitly describe theirrich attributes and connections. Correspondingly, a MOC-GAN is proposed to mixthe inputs of two modalities to generate realistic images. It firstly infersthe implicit relations between object pairs from the captions to build ahidden-state scene graph. So a multi-layer representation containing objects,relations and captions is constructed, where the scene graph provides thestructures of the scene and the caption provides the image-level guidance. Thena cascaded attentive generative network is designed to coarse-to-fine generatephrase patch by paying attention to the most relevant words in the caption. Inaddition, a phrase-wise DAMSM is proposed to better supervise the fine-grainedphrase-patch consistency. On COCO dataset, our method outperforms thestate-of-the-art methods on both Inception Score and FID while maintaining highvisual quality. Extensive experiments demonstrate the unique features of ourproposed method.

MOC-GAN: Mixing Objects and Captions to Generate Realistic Images