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

ImageNet pre-trained deep neural networks (DNNs) show notable transferabilityfor building effective image quality assessment (IQA) models. Such a remarkablebyproduct has often been identified as an emergent property in previousstudies. In this work, we attribute such capability to the intrinsictexture-sensitive characteristic that classifies images using texture features.We fully exploit this characteristic to develop a novel full-reference IQA(FR-IQA) model based exclusively on pre-trained DNN features. Specifically, wecompute the distance correlation, a highly promising yet relativelyunder-investigated statistic, between reference and distorted images in thedeep feature domain. In addition, the distance correlation quantifies bothlinear and nonlinear feature relationships, which is far beyond the widely usedfirst-order and second-order statistics in the feature space. We conductcomprehensive experiments to demonstrate the superiority of the proposedquality model on five standard IQA datasets, one perceptual similarity dataset,two texture similarity datasets, and one geometric transformation dataset.Moreover, we optimize the proposed model to generate a broad spectrum oftexture patterns, by treating the model as the style loss function for neuralstyle transfer (NST). Extensive experiments demonstrate that the proposedtexture synthesis and NST methods achieve the best quantitative and qualitativeresults. We release our code at https://github.com/h4nwei/DeepDC.

DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator