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

Nowadays neural-network-based image- and video-quality metrics show betterperformance compared to traditional methods. However, they also became morevulnerable to adversarial attacks that increase metrics' scores withoutimproving visual quality. The existing benchmarks of quality metrics comparetheir performance in terms of correlation with subjective quality andcalculation time. However, the adversarial robustness of image-quality metricsis also an area worth researching. In this paper, we analyse modern metrics'robustness to different adversarial attacks. We adopted adversarial attacksfrom computer vision tasks and compared attacks' efficiency against 15no-reference image/video-quality metrics. Some metrics showed high resistanceto adversarial attacks which makes their usage in benchmarks safer thanvulnerable metrics. The benchmark accepts new metrics submissions forresearchers who want to make their metrics more robust to attacks or to findsuch metrics for their needs. Try our benchmark using pip installrobustness-benchmark.

Comparing the robustness of modern no-reference image- and video-quality metrics to adversarial attacks