</> Code with Papers by Syntology

Papers › Approaches Toward Physical and General Video Anomaly Detection

Approaches Toward Physical and General Video Anomaly Detection

14 Dec 2021arXiv:2112.07661archive 2025-07-28

Laura Kart, Niv Cohen

In recent years, many works have addressed the problem of finding never-seen-before anomalies in videos. Yet, most work has been focused on detecting anomalous frames in surveillance videos taken from security cameras. Meanwhile, the task of anomaly detection (AD) in videos exhibiting anomalous mechanical behavior, has been mostly overlooked. Anomaly detection in such videos is both of academic and practical interest, as they may enable automatic detection of malfunctions in many manufacturing, maintenance, and real-life settings. To assess the potential of the different approaches to detect such anomalies, we evaluate two simple baseline approaches: (i) Temporal-pooled image AD techniques. (ii) Density estimation of videos represented with features pretrained for video-classification. Development of such methods calls for new benchmarks to allow evaluation of different possible approaches. We introduce the Physical Anomalous Trajectory or Motion (PHANTOM) dataset, which contains six different video classes. Each class consists of normal and anomalous videos. The classes differ in the presented phenomena, the normal class variability, and the kind of anomalies in the videos. We also suggest an even harder benchmark where anomalous activities should be spotted on highly variable scenes.

PaperPDFCode

Code

laurarkart/Physical-Anomalous-Trajectory-or-Motion-PHANTOM-Dataset officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Anomaly DetectionDensity EstimationGeneral Action Video Anomaly DetectionPhysical Video Anomaly DetectionVideo Anomaly DetectionVideo Classification

Datasets

Introduced by this paper, per the archive.

PHANTOM

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
General Action Video Anomaly Detection Something-Something V2 Pooled Image Level kNN Architecture ViT #1 of 3 Archive leaderboard report
General Action Video Anomaly Detection Something-Something V2 Pooled Image Level kNN Avg. ROC-AUC 0.58 #1 of 3 Archive leaderboard report
General Action Video Anomaly Detection Something-Something V2 Video Level features kNN Architecture TimeSformer #3 of 3 Archive leaderboard report
General Action Video Anomaly Detection Something-Something V2 Video Level features kNN Avg. ROC-AUC 0.52 #3 of 3 Archive leaderboard report
Physical Video Anomaly Detection PHANTOM Pooled Image Level kNN Architecture ViT #1 of 3 Archive leaderboard report
Physical Video Anomaly Detection PHANTOM Pooled Image Level kNN Avg. ROC-AUC 0.78 #1 of 3 Archive leaderboard report
Physical Video Anomaly Detection PHANTOM Video Level features kNN Architecture TimeSformer #2 of 3 Archive leaderboard report
Physical Video Anomaly Detection PHANTOM Video Level features kNN Avg. ROC-AUC 0.76 #2 of 3 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