Simple Yet Efficient Content Based Video Copy Detection

TL;DR

This paper introduces an efficient content-based video copy detection algorithm that uses self-similarity matrices as descriptors, achieving high accuracy and computational efficiency on benchmark datasets.

Contribution

The paper presents a novel video copy detection method utilizing self-similarity matrices, improving both speed and accuracy over existing approaches.

Findings

Achieves 100% detection score on MuscleVCD ST1 dataset.

Maintains at least 93% accuracy across various parameters.

Outperforms many existing methods in efficiency and effectiveness.

Abstract

Given a collection of videos, how to detect content-based copies efficiently with high accuracy? Detecting copies in large video collections still remains one of the major challenges of multimedia retrieval. While many video copy detection approaches show high computation times and insufficient quality, we propose a new efficient content-based video copy detection algorithm improving both aspects. The idea of our approach consists in utilizing self-similarity matrices as video descriptors in order to capture different visual properties. We benchmark our algorithm on the MuscleVCD ST1 benchmark dataset and show that our approach is able to achieve a score of 100\% and a score of at least 93\% in a wide range of parameters.