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

Video anomaly detection (VAD) is a challenging computer vision task with manypractical applications. As anomalies are inherently ambiguous, it is essentialfor users to understand the reasoning behind a system's decision in order todetermine if the rationale is sound. In this paper, we propose a simple buthighly effective method that pushes the boundaries of VAD accuracy andinterpretability using attribute-based representations. Our method representsevery object by its velocity and pose. The anomaly scores are computed using adensity-based approach. Surprisingly, we find that this simple representationis sufficient to achieve state-of-the-art performance in ShanghaiTech, thelargest and most complex VAD dataset. Combining our interpretableattribute-based representations with implicit, deep representation yieldsstate-of-the-art performance with a $99.1\%, 93.3\%$, and $85.9\%$ AUROC onPed2, Avenue, and ShanghaiTech, respectively. Our method is accurate,interpretable, and easy to implement.

Attribute-based Representations for Accurate and Interpretable Video Anomaly Detection