Papers › EVAL: Explainable Video Anomaly Localization

EVAL: Explainable Video Anomaly Localization

15 Dec 2022CVPR 2023 1arXiv:2212.07900archive 2025-07-28

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.

PaperPDFConference PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionAnomaly LocalizationVideo Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection CUHK Avenue EVAL AUC 86.02% #28 of 35 Archive leaderboard report
Anomaly Detection CUHK Avenue EVAL RBDC 68.2 #28 of 35 Archive leaderboard report
Anomaly Detection CUHK Avenue EVAL TBDC 87.56 #28 of 35 Archive leaderboard report
Anomaly Detection ShanghaiTech EVAL AUC 76.63% #22 of 31 Archive leaderboard report
Anomaly Detection ShanghaiTech EVAL RBDC 59.21 #22 of 31 Archive leaderboard report
Anomaly Detection ShanghaiTech EVAL TBDC 89.44 #22 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections