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

Significant improvement has been made on just noticeable difference (JND)modelling due to the development of deep neural networks, especially for therecently developed unsupervised-JND generation models. However, they have amajor drawback that the generated JND is assessed in the real-world signaldomain instead of in the perceptual domain in the human brain. There is anobvious difference when JND is assessed in such two domains since the visualsignal in the real world is encoded before it is delivered into the brain withthe human visual system (HVS). Hence, we propose an HVS-inspired signaldegradation network for JND estimation. To achieve this, we carefully analyzethe HVS perceptual process in JND subjective viewing to obtain relevantinsights, and then design an HVS-inspired signal degradation (HVS-SD) networkto represent the signal degradation in the HVS. On the one hand, the welllearnt HVS-SD enables us to assess the JND in the perceptual domain. On theother hand, it provides more accurate prior information for better guiding JNDgeneration. Additionally, considering the requirement that reasonable JNDshould not lead to visual attention shifting, a visual attention loss isproposed to control JND generation. Experimental results demonstrate that theproposed method achieves the SOTA performance for accurately estimating theredundancy of the HVS. Source code will be available athttps://github.com/jianjin008/HVS-SD-JND.

HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation