Adaptive Video Anomaly Detection by Attention-Based Relational Knowledge Distillation

Basit Öğe Kaydı
dc.contributor.authorAsal, Burcak
dc.contributor.authorCan, Ahmet Burak
dc.date.accessioned2026-02-27T07:33:13Z
dc.date.available2026-02-27T07:33:13Z
dc.date.issued2025
dc.description.abstractDetecting anomaly patterns in videos is a challenging task due to complex scenes, huge diversity of anomalies, and fuzzy nature of the task. With advent of technology, tremendous size of visual data is being generated by video surveillance systems, which makes harder to search, analyze, and detect anomalies on video data by human operators. In this paper, we introduce three relational distillation approaches to handle both robust detection of anomalous events and gradual adaptation to different anomaly patterns in new videos while not forgetting anomaly patterns learned from the previous video data. In order to realize these concepts, we propose a unique attention mechanism with feature and relation based knowledge distillation methods. We adapted our knowledge distillation methods to two state-of-the-art models designed for anomaly detection task. Our extensive experiments on two public datasets show that not only our best version model achieves robust performance with a frame-level AUC of 80.22 on UCF-Crime and video-level AUC of 78.20 on RWF-2000 datasets but also the proposed distillation methods improve the performance while reducing catastrophic forgetting problem.
dc.description.sponsorshipScientific and Technological Research Council of Turkiye (TUBIdot;TAK) [119E098]; Hacettepe University Scientific Research Projects Coordination Department [FHD-2022-20044]
dc.description.sponsorshipThis work was supported in part by the Scientific and Technological Research Council of Turkiye (TUB & Idot;TAK) under Grant 119E098, and in part by Hacettepe University Scientific Research Projects Coordination Department under Grant FHD-2022-20044.
dc.identifier.doi10.1109/ACCESS.2025.3585984
dc.identifier.endpage117185
dc.identifier.issn2169-3536
dc.identifier.startpage117170
dc.identifier.urihttp://dx.doi.org/10.1109/ACCESS.2025.3585984
dc.identifier.urihttps://hdl.handle.net/20.500.14669/4496
dc.identifier.volume13
dc.identifier.wosWOS:001527231900029
dc.indekslendigikaynakWeb of Science
dc.language.isoen
dc.publisherIEEE-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIEEEAccess
dc.relation.publicationcategoryMakale - Uluslararas� Hakemli Dergi - Kurum ��retim Eleman�
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20260302
dc.subjectAnomaly detection
dc.subjectAdaptation models
dc.subjectTraining
dc.subjectData models
dc.subjectFeature extraction
dc.subjectDeep learning
dc.subjectWeak supervision
dc.subjectLong short term memory
dc.subjectNoise
dc.subjectKnowledge engineering
dc.subjectAR-Net
dc.subjectcomputer vision
dc.subjectGCN
dc.subjectknowledge distillation
dc.subjectrelational approaches
dc.subjectvideo anomaly detection
dc.subjectweak supervision
dc.titleAdaptive Video Anomaly Detection by Attention-Based Relational Knowledge Distillation
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu