ComplexVAD: Detecting Interaction Anomalies in Video

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mumcu, Furkan, Jones, Michael J., Yilmaz, Yasin, Cherian, Anoop
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917893962203136
author Mumcu, Furkan
Jones, Michael J.
Yilmaz, Yasin
Cherian, Anoop
author_facet Mumcu, Furkan
Jones, Michael J.
Yilmaz, Yasin
Cherian, Anoop
contents Existing video anomaly detection datasets are inadequate for representing complex anomalies that occur due to the interactions between objects. The absence of complex anomalies in previous video anomaly detection datasets affects research by shifting the focus onto simple anomalies. To address this problem, we introduce a new large-scale dataset: ComplexVAD. In addition, we propose a novel method to detect complex anomalies via modeling the interactions between objects using a scene graph with spatio-temporal attributes. With our proposed method and two other state-of-the-art video anomaly detection methods, we obtain baseline scores on ComplexVAD and demonstrate that our new method outperforms existing works.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09733
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ComplexVAD: Detecting Interaction Anomalies in Video
Mumcu, Furkan
Jones, Michael J.
Yilmaz, Yasin
Cherian, Anoop
Computer Vision and Pattern Recognition
Existing video anomaly detection datasets are inadequate for representing complex anomalies that occur due to the interactions between objects. The absence of complex anomalies in previous video anomaly detection datasets affects research by shifting the focus onto simple anomalies. To address this problem, we introduce a new large-scale dataset: ComplexVAD. In addition, we propose a novel method to detect complex anomalies via modeling the interactions between objects using a scene graph with spatio-temporal attributes. With our proposed method and two other state-of-the-art video anomaly detection methods, we obtain baseline scores on ComplexVAD and demonstrate that our new method outperforms existing works.
title ComplexVAD: Detecting Interaction Anomalies in Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.09733