# Anomaly Detection in Video Sequence with Appearance-Motion Correspondence

## TL;DR

This paper introduces a deep CNN that detects anomalies in surveillance videos by learning the correspondence between object appearances and motions, trained solely on normal events, and achieving competitive results on benchmark datasets.

## Contribution

It presents a novel CNN architecture combining reconstruction and image translation networks to model appearance-motion correspondence for anomaly detection.

## Key findings

- Achieves state-of-the-art performance on 6 benchmark datasets.
- Effectively detects anomalies using only normal event videos for training.
- Demonstrates robustness across diverse surveillance scenarios.

## Abstract

Anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. We propose a deep convolutional neural network (CNN) that addresses this problem by learning a correspondence between common object appearances (e.g. pedestrian, background, tree, etc.) and their associated motions. Our model is designed as a combination of a reconstruction network and an image translation model that share the same encoder. The former sub-network determines the most significant structures that appear in video frames and the latter one attempts to associate motion templates to such structures. The training stage is performed using only videos of normal events and the model is then capable to estimate frame-level scores for an unknown input. The experiments on 6 benchmark datasets demonstrate the competitive performance of the proposed approach with respect to state-of-the-art methods.