Cover Image

A deep Spatio-temporal network for vision-based sexual harassment detection

Smart surveillance systems can play a significant role in detecting sexual harassment in real-time for law enforcement which can reduce the sexual harassment activities. Real-time detecting of sexual harassment from video is a complex computer vision because of various factors such as clothing or ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Islam, Md Shamimul, Hasan, Md Mahedi, Abdullah, Sohaib, Md Akbar, Jalal Uddin, Arafat, N. H.M., Murad, Saydul Akbar
Format: Conference or Workshop Item
Language:English
English
Published: Institute of Electrical and Electronics Engineers Inc. 2021
Subjects:
QA75 Electronic computers. Computer science
QA76 Computer software
T Technology (General)
TA Engineering (General). Civil engineering (General)
Online Access:http://umpir.ump.edu.my/id/eprint/42383/1/A%20deep%20Spatio-temporal%20network%20for%20vision-based%20sexual.pdf
http://umpir.ump.edu.my/id/eprint/42383/2/A%20deep%20Spatio-temporal%20network%20for%20vision-based%20sexual%20harassment%20detection_ABS.pdf
http://umpir.ump.edu.my/id/eprint/42383/
https://doi.org/10.1109/ETCCE54784.2021.9689891
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.42383
record_format eprints
spelling my.ump.umpir.423832024-10-30T04:38:35Z http://umpir.ump.edu.my/id/eprint/42383/ A deep Spatio-temporal network for vision-based sexual harassment detection Islam, Md Shamimul Hasan, Md Mahedi Abdullah, Sohaib Md Akbar, Jalal Uddin Arafat, N. H.M. Murad, Saydul Akbar QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) Smart surveillance systems can play a significant role in detecting sexual harassment in real-time for law enforcement which can reduce the sexual harassment activities. Real-time detecting of sexual harassment from video is a complex computer vision because of various factors such as clothing or carrying variation, illumination variation, partial occlusion, low resolution, view angle variation etc. Due to the advancement of convolutional neural networks (CNNs) and Long Short-Term Memory (LSTM), human action recognition tasks have achieved great success in recent years. But sexual harassment detection is addressed due to presences of large-scale harassment dataset. In this work, to address this problem, we build a video dataset of sexual harassment, namely Sexual harassment video (SHV) dataset which consists of harassment and non-harassment videos collected from YouTube. Besides, we build a CNN-LSTM network to detect the sexual harassment in which CNN and RNN are employed for extracting spatial features and temporal features, respectively. State-of-the-art pretrained models are also employed as a spatial feature extractor with an LSTM and three dense layer to classify harassment activities. Moreover, to find the robustness of our proposed model, we have conducted several experiments with our proposed method on two other benchmark datasets, such as Hockey Fight dataset and Movie Violence dataset and achieved state-of-the-art accuracy. Institute of Electrical and Electronics Engineers Inc. 2021 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/42383/1/A%20deep%20Spatio-temporal%20network%20for%20vision-based%20sexual.pdf pdf en http://umpir.ump.edu.my/id/eprint/42383/2/A%20deep%20Spatio-temporal%20network%20for%20vision-based%20sexual%20harassment%20detection_ABS.pdf Islam, Md Shamimul and Hasan, Md Mahedi and Abdullah, Sohaib and Md Akbar, Jalal Uddin and Arafat, N. H.M. and Murad, Saydul Akbar (2021) A deep Spatio-temporal network for vision-based sexual harassment detection. In: 2021 Emerging Technology in Computing, Communication and Electronics, ETCCE 2021. 2021 Emerging Technology in Computing, Communication and Electronics, ETCCE 2021 , 21 - 23 December 2021 , Dhaka. pp. 1-6.. ISBN 978-166548364-3 (Published) https://doi.org/10.1109/ETCCE54784.2021.9689891
institution Universiti Malaysia Pahang Al-Sultan Abdullah
building UMPSA Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang Al-Sultan Abdullah
content_source UMPSA Institutional Repository
url_provider http://umpir.ump.edu.my/
language English
English
topic QA75 Electronic computers. Computer science
QA76 Computer software
T Technology (General)
TA Engineering (General). Civil engineering (General)
spellingShingle QA75 Electronic computers. Computer science
QA76 Computer software
T Technology (General)
TA Engineering (General). Civil engineering (General)
Islam, Md Shamimul
Hasan, Md Mahedi
Abdullah, Sohaib
Md Akbar, Jalal Uddin
Arafat, N. H.M.
Murad, Saydul Akbar
A deep Spatio-temporal network for vision-based sexual harassment detection
description Smart surveillance systems can play a significant role in detecting sexual harassment in real-time for law enforcement which can reduce the sexual harassment activities. Real-time detecting of sexual harassment from video is a complex computer vision because of various factors such as clothing or carrying variation, illumination variation, partial occlusion, low resolution, view angle variation etc. Due to the advancement of convolutional neural networks (CNNs) and Long Short-Term Memory (LSTM), human action recognition tasks have achieved great success in recent years. But sexual harassment detection is addressed due to presences of large-scale harassment dataset. In this work, to address this problem, we build a video dataset of sexual harassment, namely Sexual harassment video (SHV) dataset which consists of harassment and non-harassment videos collected from YouTube. Besides, we build a CNN-LSTM network to detect the sexual harassment in which CNN and RNN are employed for extracting spatial features and temporal features, respectively. State-of-the-art pretrained models are also employed as a spatial feature extractor with an LSTM and three dense layer to classify harassment activities. Moreover, to find the robustness of our proposed model, we have conducted several experiments with our proposed method on two other benchmark datasets, such as Hockey Fight dataset and Movie Violence dataset and achieved state-of-the-art accuracy.
format Conference or Workshop Item
author Islam, Md Shamimul
Hasan, Md Mahedi
Abdullah, Sohaib
Md Akbar, Jalal Uddin
Arafat, N. H.M.
Murad, Saydul Akbar
author_facet Islam, Md Shamimul
Hasan, Md Mahedi
Abdullah, Sohaib
Md Akbar, Jalal Uddin
Arafat, N. H.M.
Murad, Saydul Akbar
author_sort Islam, Md Shamimul
title A deep Spatio-temporal network for vision-based sexual harassment detection
title_short A deep Spatio-temporal network for vision-based sexual harassment detection
title_full A deep Spatio-temporal network for vision-based sexual harassment detection
title_fullStr A deep Spatio-temporal network for vision-based sexual harassment detection
title_full_unstemmed A deep Spatio-temporal network for vision-based sexual harassment detection
title_sort deep spatio-temporal network for vision-based sexual harassment detection
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2021
url http://umpir.ump.edu.my/id/eprint/42383/1/A%20deep%20Spatio-temporal%20network%20for%20vision-based%20sexual.pdf
http://umpir.ump.edu.my/id/eprint/42383/2/A%20deep%20Spatio-temporal%20network%20for%20vision-based%20sexual%20harassment%20detection_ABS.pdf
http://umpir.ump.edu.my/id/eprint/42383/
https://doi.org/10.1109/ETCCE54784.2021.9689891
_version_ 1822924727872651264
score 13.232432

Similar Items