Balancing Accuracy and Training Time in Federated Learning for Violence Detection in Surveillance Videos: A Study of Neural Network Architectures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quentin, Pajon, Swan, Serre, Hugo, Wissocq, Léo, Rabaud, Siba, Haidar, Antoun, Yaacoub
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910914486206464
author Quentin, Pajon
Swan, Serre
Hugo, Wissocq
Léo, Rabaud
Siba, Haidar
Antoun, Yaacoub
author_facet Quentin, Pajon
Swan, Serre
Hugo, Wissocq
Léo, Rabaud
Siba, Haidar
Antoun, Yaacoub
contents This paper presents an investigation into machine learning techniques for violence detection in videos and their adaptation to a federated learning context. The study includes experiments with spatio-temporal features extracted from benchmark video datasets, comparison of different methods, and proposal of a modified version of the "Flow-Gated" architecture called "Diff-Gated." Additionally, various machine learning techniques, including super-convergence and transfer learning, are explored, and a method for adapting centralized datasets to a federated learning context is developed. The research achieves better accuracy results compared to state-of-the-art models by training the best violence detection model in a federated learning context.
format Preprint
id arxiv_https___arxiv_org_abs_2308_05106
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Balancing Accuracy and Training Time in Federated Learning for Violence Detection in Surveillance Videos: A Study of Neural Network Architectures
Quentin, Pajon
Swan, Serre
Hugo, Wissocq
Léo, Rabaud
Siba, Haidar
Antoun, Yaacoub
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
This paper presents an investigation into machine learning techniques for violence detection in videos and their adaptation to a federated learning context. The study includes experiments with spatio-temporal features extracted from benchmark video datasets, comparison of different methods, and proposal of a modified version of the "Flow-Gated" architecture called "Diff-Gated." Additionally, various machine learning techniques, including super-convergence and transfer learning, are explored, and a method for adapting centralized datasets to a federated learning context is developed. The research achieves better accuracy results compared to state-of-the-art models by training the best violence detection model in a federated learning context.
title Balancing Accuracy and Training Time in Federated Learning for Violence Detection in Surveillance Videos: A Study of Neural Network Architectures
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2308.05106