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

Human behavior anomaly detection aims to identify unusual human actions,playing a crucial role in intelligent surveillance and other areas. The currentmainstream methods still adopt reconstruction or future frame predictiontechniques. However, reconstructing or predicting low-level pixel featureseasily enables the network to achieve overly strong generalization ability,allowing anomalies to be reconstructed or predicted as effectively as normaldata. Different from their methods, inspired by the Student-Teacher Network, wepropose a novel framework called the Multilevel Guidance-ExplorationNetwork(MGENet), which detects anomalies through the difference in high-levelrepresentation between the Guidance and Exploration network. Specifically, wefirst utilize the pre-trained Normalizing Flow that takes skeletal keypoints asinput to guide an RGB encoder, which takes unmasked RGB frames as input, toexplore motion latent features. Then, the RGB encoder guides the mask encoder,which takes masked RGB frames as input, to explore the latent appearancefeature. Additionally, we design a Behavior-Scene Matching Module(BSMM) todetect scene-related behavioral anomalies. Extensive experiments demonstratethat our proposed method achieves state-of-the-art performance on ShanghaiTechand UBnormal datasets, with AUC of 86.9 % and 73.5 %, respectively. The codewill be available on https://github.com/molu-ggg/GENet.

A Multilevel Guidance-Exploration Network and Behavior-Scene Matching Method for Human Behavior Anomaly Detection