EVAL: Explainable Video Anomaly Localization

15 Dec 2022  ·  Ashish Singh, Michael J. Jones, Erik Learned-Miller ·

We develop a novel framework for single-scene video anomaly localization that allows for human-understandable reasons for the decisions the system makes. We first learn general representations of objects and their motions (using deep networks) and then use these representations to build a high-level, location-dependent model of any particular scene. This model can be used to detect anomalies in new videos of the same scene. Importantly, our approach is explainable - our high-level appearance and motion features can provide human-understandable reasons for why any part of a video is classified as normal or anomalous. We conduct experiments on standard video anomaly detection datasets (Street Scene, CUHK Avenue, ShanghaiTech and UCSD Ped1, Ped2) and show significant improvements over the previous state-of-the-art.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Anomaly Detection CUHK Avenue EVAL AUC 86.02% # 20
RBDC 68.2 # 1
TBDC 87.56 # 2
Anomaly Detection ShanghaiTech EVAL AUC 76.63% # 14
RBDC 59.21 # 1
TBDC 89.44 # 1


No methods listed for this paper. Add relevant methods here