# Unmasking the abnormal events in video

## TL;DR

This paper introduces a novel, training-free video abnormal event detection framework based on unmasking, achieving real-time performance and state-of-the-art accuracy on benchmark datasets.

## Contribution

It adapts the unmasking technique from text authorship verification to video abnormal event detection, a first in computer vision.

## Key findings

- Achieves state-of-the-art results on benchmark datasets.
- Operates in real-time at 20 frames per second.
- Requires no training sequences.

## Abstract

We propose a novel framework for abnormal event detection in video that requires no training sequences. Our framework is based on unmasking, a technique previously used for authorship verification in text documents, which we adapt to our task. We iteratively train a binary classifier to distinguish between two consecutive video sequences while removing at each step the most discriminant features. Higher training accuracy rates of the intermediately obtained classifiers represent abnormal events. To the best of our knowledge, this is the first work to apply unmasking for a computer vision task. We compare our method with several state-of-the-art supervised and unsupervised methods on four benchmark data sets. The empirical results indicate that our abnormal event detection framework can achieve state-of-the-art results, while running in real-time at 20 frames per second.