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

While impressive performance has been achieved in image captioning, thelimited diversity of the generated captions and the large parameter scaleremain major barriers to the real-word application of these systems. In thiswork, we propose a lightweight image captioning network in combination withcontinuous diffusion, called Prefix-diffusion. To achieve diversity, we designan efficient method that injects prefix image embeddings into the denoisingprocess of the diffusion model. In order to reduce trainable parameters, weemploy a pre-trained model to extract image features and further design anextra mapping network. Prefix-diffusion is able to generate diverse captionswith relatively less parameters, while maintaining the fluency and relevance ofthe captions benefiting from the generative capabilities of the diffusionmodel. Our work paves the way for scaling up diffusion models for imagecaptioning, and achieves promising performance compared with recent approaches.

Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning