A Discriminative Framework for Anomaly Detection in Large Videos

TL;DR

This paper introduces a discriminative, unsupervised framework for anomaly detection in large videos that does not rely on temporal order or training data, achieving state-of-the-art results.

Contribution

It proposes a novel anomaly detection approach based on discriminative learning that is independent of temporal ordering and does not require training sequences.

Findings

Achieves state-of-the-art results on standard datasets without training data.

Effective in detecting anomalies in complex, long videos.

Outperforms classical density estimation methods.

Abstract

We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These algorithms are sensitive to the order in which anomalies appear and require either training data or early context assumptions that do not hold for longer, more complex videos. By defining anomalies as examples that can be distinguished from other examples in the same video, our definition inspires a shift in approaches from classical density estimation to simple discriminative learning. Our contributions include a novel framework for anomaly detection that is (1) independent of temporal ordering of anomalies, and (2) unsupervised, requiring no separate training sequences. We show that our algorithm can achieve state-of-the-art results even when we adjust the setting by removing training sequences from standard datasets.