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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

To leverage deep learning for image aesthetics assessment, one critical butunsolved issue is how to seamlessly incorporate the information of image aspectratios to learn more robust models. In this paper, an adaptive fractionaldilated convolution (AFDC), which is aspect-ratio-embedded,composition-preserving and parameter-free, is developed to tackle this issuenatively in convolutional kernel level. Specifically, the fractional dilatedkernel is adaptively constructed according to the image aspect ratios, wherethe interpolation of nearest two integers dilated kernels is used to cope withthe misalignment of fractional sampling. Moreover, we provide a conciseformulation for mini-batch training and utilize a grouping strategy to reducecomputational overhead. As a result, it can be easily implemented by commondeep learning libraries and plugged into popular CNN architectures in acomputation-efficient manner. Our experimental results demonstrate that ourproposed method achieves state-of-the-art performance on image aestheticsassessment over the AVA dataset.

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment