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

Weakly supervised video anomaly detection aims to identify abnormal events invideos using only video-level labels. Recently, two-stage self-training methodshave achieved significant improvements by self-generating pseudo labels andself-refining anomaly scores with these labels. As the pseudo labels play acrucial role, we propose an enhancement framework by exploiting completenessand uncertainty properties for effective self-training. Specifically, we firstdesign a multi-head classification module (each head serves as a classifier)with a diversity loss to maximize the distribution differences of predictedpseudo labels across heads. This encourages the generated pseudo labels tocover as many abnormal events as possible. We then devise an iterativeuncertainty pseudo label refinement strategy, which improves not only theinitial pseudo labels but also the updated ones obtained by the desiredclassifier in the second stage. Extensive experimental results demonstrate theproposed method performs favorably against state-of-the-art approaches on theUCF-Crime, TAD, and XD-Violence benchmark datasets.

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection