MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection

Yingxian CHEN, Zhengzhe LIU, Baoheng ZHANG, Wilton FOK, Xiaojuan QI, Yik-Chung WU

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

57 Citations (Scopus)

Abstract

Weakly supervised detection of anomalies in surveillance videos is a challenging task. Going beyond existing works that have deficient capabilities to localize anomalies in long videos, we propose a novel glance and focus network to effectively integrate spatial-temporal information for accurate anomaly detection. In addition, we empirically found that existing approaches that use feature magnitudes to represent the degree of anomalies typically ignore the effects of scene variations, and hence result in sub-optimal performance due to the inconsistency of feature magnitudes across scenes. To address this issue, we propose the Feature Amplification Mechanism and a Magnitude Contrastive Loss to enhance the discriminativeness of feature magnitudes for detecting anomalies. Experimental results on two large-scale benchmarks UCF-Crime and XD-Violence manifest that our method outperforms state-of-the-art approaches.
Original languageEnglish
Title of host publicationProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
EditorsBrian WILLIAMS, Yiling CHEN, Jennifer NEVILLE
PublisherAAAI press
Pages387-395
Number of pages9
ISBN (Electronic)9781577358800
DOIs
Publication statusPublished - 26 Jun 2023
Externally publishedYes

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAssociation for the Advancement of Artificial Intelligence
Number1
Volume37
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Bibliographical note

Publisher Copyright:
Copyright © 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Funding

This work was supported by the Smart Traffic Fund (PSRI/27/2201/PR) funded by the Hong Kong Productivity Council and the Transport Department of HKSAR.

Fingerprint

Dive into the research topics of 'MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection'. Together they form a unique fingerprint.

Cite this