Papers › Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos

Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos

8 Mar 2019CVPR 2019 6arXiv:1903.03295archive 2025-07-28

Romero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, Svetha Venkatesh

Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features. We decompose the skeletal movements into two sub-components: global body movement and local body posture. We model the dynamics and interaction of the coupled features in our novel Message-Passing Encoder-Decoder Recurrent Network. We observed that the decoupled features collaboratively interact in our spatio-temporal model to accurately identify human-related irregular events from surveillance video sequences. Compared to traditional appearance-based models, our method achieves superior outlier detection performance. Our model also offers "open-box" examination and decision explanation made possible by the semantically understandable features and a network architecture supporting interpretability.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

RomeroBarata/skeleton_based_anomaly_detection officialmentioned in papermentioned 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 DetectionDecoderOutlier DetectionVideo Anomaly Detection

Datasets

Introduced by this paper, per the archive.

HR-AvenueHR-ShanghaiTech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection ShanghaiTech MPED-RNN AUC 73.40% #27 of 31 Archive leaderboard report
Video Anomaly Detection HR-Avenue MPED-RNN AUC 86.3 #7 of 11 Archive leaderboard report
Video Anomaly Detection HR-ShanghaiTech MPED-RNN AUC 75.4 #9 of 14 Archive leaderboard report
Video Anomaly Detection HR-UBnormal MPED-RNN AUC 61.2 #6 of 8 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