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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2021
|
| Subjects: | |
| 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 |
| _version_ | 1825815869296476160 |
|---|---|
| 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 |
| collection | UMP |
| 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. |
| first_indexed | 2024-12-09T02:30:07Z |
| format | Conference or Workshop Item |
| id | UMPir42383 |
| institution | Universiti Malaysia Pahang |
| language | English English |
| last_indexed | 2024-12-09T02:30:07Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | UMPir423832024-10-30T04:38:35Z 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 |
| 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 |
| title | 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_short | A deep Spatio-temporal network for vision-based sexual harassment detection |
| title_sort | deep spatio temporal network for vision based sexual harassment detection |
| topic | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) |
| 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 |
| work_keys_str_mv | AT islammdshamimul adeepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT hasanmdmahedi adeepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT abdullahsohaib adeepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT mdakbarjalaluddin adeepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT arafatnhm adeepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT muradsaydulakbar adeepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT islammdshamimul deepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT hasanmdmahedi deepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT abdullahsohaib deepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT mdakbarjalaluddin deepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT arafatnhm deepspatiotemporalnetworkforvisionbasedsexualharassmentdetection AT muradsaydulakbar deepspatiotemporalnetworkforvisionbasedsexualharassmentdetection |