Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows

TL;DR

This paper presents a novel unsupervised human action anomaly detection method using normalizing flows, incorporating multi-level analysis and frequency domain transformation to improve detection of localized and global anomalies.

Contribution

The paper introduces a multi-level normalizing flow framework with frequency domain processing for improved unsupervised human action anomaly detection.

Findings

Outperforms existing methods on benchmark datasets

Effectively detects both global and local motion anomalies

Utilizes frequency domain features to enhance robustness

Abstract

We introduce the task of human action anomaly detection (HAAD), which aims to identify anomalous motions in an unsupervised manner given only the pre-determined normal category of training action samples. Compared to prior human-related anomaly detection tasks which primarily focus on unusual events from videos, HAAD involves the learning of specific action labels to recognize semantically anomalous human behaviors. To address this task, we propose a normalizing flow (NF)-based detection framework where the sample likelihood is effectively leveraged to indicate anomalies. As action anomalies often occur in some specific body parts, in addition to the full-body action feature learning, we incorporate extra encoding streams into our framework for a finer modeling of body subsets. Our framework is thus multi-level to jointly discover global and local motion anomalies. Furthermore, to show awareness of the potentially jittery data during recording, we resort to discrete cosine transformation by converting the action samples from the temporal to the frequency domain to mitigate the issue of data instability. Extensive experimental results on two human action datasets demonstrate that our method outperforms the baselines formed by adapting state-of-the-art human activity AD approaches to our task of HAAD.