Comparative Analysis: Violence Recognition from Videos using Transfer Learning

Dursun Dashdamirov
8/26/2024
cs.CV

No official code found. Best implementation: DDursun/Violence-Detection (0 stars, last commit 2024-08-30).

Abstract

Action recognition has become a hot topic in computer vision. However, the main applications of computer vision in video processing have focused on detection of relatively simple actions while complex events such as violence detection have been comparatively less investigated. This study focuses on the benchmarking of various deep learning techniques on a complex dataset. Next, a larger dataset is utilized to test the uplift from increasing volume of data. The dataset size increase from 500 to 1,600 videos resulted in a notable average accuracy improvement of 6% across four models.

View on arXivView PDF

Code Implementations(1)

DDursun/Violence-DetectionCommunity100%
00Jupyter NotebookAug 17, 20242 years ago

Similar Papers

Application of Attention Mechanism with Bidirectional Long Short-Term Memory (BiLSTM) and CNN for Human Conflict Detection using Computer Vision

87% match2025

A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities

87% match2024

SMART-Vision: Survey of Modern Action Recognition Techniques in Vision

86% match2025

Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis

85% match2025

Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications

85% match2025

Barcode and QR Code Object Detection: An Experimental Study on YOLOv8 Models

85% match2025

Cite this paper

@article{dashdamirov2024comparative,
  title  = {Comparative Analysis: Violence Recognition from Videos using Transfer Learning},
  author = {Dursun Dashdamirov},
  year   = {2024},
  eprint = {2408.14659},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.14659v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.14659.svg)](https://codeofpaper.com/paper/2408.14659)

Discussion