Citation

Convertini N, Dentamaro V, Impedovo D, Pirlo G, Sarcinella L. Information (Basel) 2020; 11(6): e321.

Copyright

(Copyright © 2020, MDPI: Multidisciplinary Digital Publications Institute)

DOI

10.3390/info11060321

PMID

unavailable

Abstract

This benchmarking study aims to examine and discuss the current state-of-the-art techniques for in-video violence detection, and also provide benchmarking results as a reference for the future accuracy baseline of violence detection systems. In this paper, the authors review 11 techniques for in-video violence detection. They re-implement five carefully chosen state-of-the-art techniques over three different and publicly available violence datasets, using several classifiers, all in the same conditions. The main contribution of this work is to compare feature-based violence detection techniques and modern deep-learning techniques, such as Inception V3.

Language: en

Keywords

benchmark video violence; Blobs; ConvLSTM; IFV; Inception V3; MoSIFT; OViF; ViF; violence video detection