Counteracting temporal attacks in Video Copy Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fojcik, Katarzyna, Syga, Piotr
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913656346771456
author Fojcik, Katarzyna
Syga, Piotr
author_facet Fojcik, Katarzyna
Syga, Piotr
contents Video Copy Detection (VCD) plays a crucial role in copyright protection and content verification by identifying duplicates and near-duplicates in large-scale video databases. The META AI Challenge on video copy detection provided a benchmark for evaluating state-of-the-art methods, with the Dual-level detection approach emerging as a winning solution. This method integrates Video Editing Detection and Frame Scene Detection to handle adversarial transformations and large datasets efficiently. However, our analysis reveals significant limitations in the VED component, particularly in its ability to handle exact copies. Moreover, Dual-level detection shows vulnerability to temporal attacks. To address it, we propose an improved frame selection strategy based on local maxima of interframe differences, which enhances robustness against adversarial temporal modifications while significantly reducing computational overhead. Our method achieves an increase of 1.4 to 5.8 times in efficiency over the standard 1 FPS approach. Compared to Dual-level detection method, our approach maintains comparable micro-average precision ($μ$AP) while also demonstrating improved robustness against temporal attacks. Given 56\% reduced representation size and the inference time of more than 2 times faster, our approach is more suitable to real-world resource restriction.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11171
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Counteracting temporal attacks in Video Copy Detection
Fojcik, Katarzyna
Syga, Piotr
Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Machine Learning
Multimedia
Video Copy Detection (VCD) plays a crucial role in copyright protection and content verification by identifying duplicates and near-duplicates in large-scale video databases. The META AI Challenge on video copy detection provided a benchmark for evaluating state-of-the-art methods, with the Dual-level detection approach emerging as a winning solution. This method integrates Video Editing Detection and Frame Scene Detection to handle adversarial transformations and large datasets efficiently. However, our analysis reveals significant limitations in the VED component, particularly in its ability to handle exact copies. Moreover, Dual-level detection shows vulnerability to temporal attacks. To address it, we propose an improved frame selection strategy based on local maxima of interframe differences, which enhances robustness against adversarial temporal modifications while significantly reducing computational overhead. Our method achieves an increase of 1.4 to 5.8 times in efficiency over the standard 1 FPS approach. Compared to Dual-level detection method, our approach maintains comparable micro-average precision ($μ$AP) while also demonstrating improved robustness against temporal attacks. Given 56\% reduced representation size and the inference time of more than 2 times faster, our approach is more suitable to real-world resource restriction.
title Counteracting temporal attacks in Video Copy Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Information Retrieval
Machine Learning
Multimedia
url https://arxiv.org/abs/2501.11171