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

In this paper, we investigate the problem of text-to-pedestrian synthesis,which has many potential applications in art, design, and video surveillance.Existing methods for text-to-bird/flower synthesis are still far from solvingthis fine-grained image generation problem, due to the complex structure andheterogeneous appearance that the pedestrians naturally take on. To this end,we propose the Multi-Grained Discrimination enhanced Generative AdversarialNetwork, that capitalizes a human-part-based Discriminator (HPD) and aself-cross-attended (SCA) global Discriminator in order to capture thecoherence of the complex body structure. A fined-grained word-level attentionmechanism is employed in the HPD module to enforce diversified appearance andvivid details. In addition, two pedestrian generation metrics, named Pose Scoreand Pose Variance, are devised to evaluate the generation quality anddiversity, respectively. We conduct extensive experiments and ablation studieson the caption-annotated pedestrian dataset, CUHK Person Description Dataset.The substantial improvement over the various metrics demonstrates the efficacyof MGD-GAN on the text-to-pedestrian synthesis scenario.

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination