NFlowAD: A normalizing flow model for anomaly detection in human motion animations

Anomaly detection has been extensively investigated in numerous application areas. Hand-crafted rules have gradually given way to supervised classification techniques, which frequently rely on a small number of anomaly labels and related architectures. When it comes to human motion, abnormalities emerge at a fine-grained temporal or joint level rather than over a whole video sequence. This study introduces NFlowAD, a self-supervised system that analyzes body joints to detect irregularities in human motion. It blends normalizing flows with masked motion modeling to describe normal motion data without the need for anomaly labels. Inference uses both reconstruction mistakes and flow-based likelihoods to detect anomalies. The validation pipeline on various state-of-the-art datasets demonstrates NFlowAD’s efficiency in recognizing, locating, and analyzing anomalous motion sequences, while maintaining robust detection and interpretability. • Provides NflowAD, a self-supervised technique that uses masked motion modeling in conjunction with normalizing flows to simulate typical human motion. • Identifies and locates small joint-level or temporal motion anomalies using a hybrid inference approach that combines reconstruction error with flow- based probability. • Exhibits excellent interpretability, robustness, and accuracy for identifying and evaluating abnormal human motion across a number of benchmark datasets.