Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approach

TL;DR

This paper reviews the use of divide and conquer strategies in video anomaly detection, introduces a new approach combining human skeletal frameworks with video analysis, and achieves state-of-the-art results on the ShanghaiTech dataset.

Contribution

It provides a comprehensive review of divide and conquer methods in video anomaly detection and proposes a novel skeletal framework-based approach that outperforms existing methods.

Findings

Achieved state-of-the-art performance on ShanghaiTech dataset

Demonstrated the effectiveness of skeletal frameworks in anomaly detection

Reviewed diverse perspectives of divide and conquer in the field

Abstract

Video anomaly detection is a complex task, and the principle of "divide and conquer" is often regarded as an effective approach to tackling intricate issues. It's noteworthy that recent methods in video anomaly detection have revealed the application of the divide and conquer philosophy (albeit with distinct perspectives from traditional usage), yielding impressive outcomes. This paper systematically reviews these literatures from six dimensions, aiming to enhance the use of the divide and conquer strategy in video anomaly detection. Furthermore, based on the insights gained from this review, a novel approach is presented, which integrates human skeletal frameworks with video data analysis techniques. This method achieves state-of-the-art performance on the ShanghaiTech dataset, surpassing all existing advanced methods.