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 in surveillance systems with only video-level labels(i.e. weakly-supervised) is challenging. This is due to, (i) the complexintegration of human and scene based anomalies comprising of subtle and sharpspatio-temporal cues in real-world scenarios, (ii) non-optimal optimizationbetween normal and anomaly instances under weak supervision. In this paper, wepropose a Human-Scene Network to learn discriminative representations bycapturing both subtle and strong cues in a dissociative manner. In addition, aself-rectifying loss is also proposed that dynamically computes the pseudotemporal annotations from video-level labels for optimizing the Human-SceneNetwork effectively. The proposed Human-Scene Network optimized withself-rectifying loss is validated on three publicly available datasets i.e.UCF-Crime, ShanghaiTech and IITB-Corridor, outperforming recently reportedstate-of-the-art approaches on five out of the six scenarios considered.

Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection