Adaptive and effective spatio-temporal modelling for offensive video classification using deep neural network

被引:5
作者
Chelliah, Balika J. J. [1 ]
Harshitha, K. [1 ]
Pandey, Saharsh [1 ]
机构
[1] SRM Inst Sci & Technol, Dept Comp Sci & Engn, Chennai, Tamil Nadu, India
关键词
deep learning; surveillance video systems; violence detection; transfer learning; motion vector; neural network; FEATURE-EXTRACTION; FACE RECOGNITION; FUSION;
D O I
10.1504/IJIEI.2023.130712
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Security cameras have recently been widely implemented in public locations, and the overall crime rate has decreased dramatically due to these omnipresent gadgets. These cameras are typically employed to offer cues and evidence after crimes have occurred rather than to prevent or deter criminal activity in the first place. Manually monitoring a lot of video footage from surveillance cameras takes significant time and effort. As a result, it is critical to automatically recognise aggressive actions from video signals. It is also critical to detect violence in videos to protect children from inappropriate content. This paper tackles the difficult subject of detecting violence in videos. Unlike previous work focusing on merging multimodal features, we take it further by including and utilising visual subtypes connected to violence. The proposed approach is implemented using Jupyter notebook and Tensorflow, with better accuracy of 76.79% on the proposed database test set.
引用
收藏
页码:19 / 34
页数:17
相关论文
共 50 条
  • [41] A Spatio-Temporal Convolutional Neural Network for Skeletal Action Recognition
    Hu, Lizhang
    Xu, Jinhua
    NEURAL INFORMATION PROCESSING (ICONIP 2017), PT III, 2017, 10636 : 377 - 385
  • [42] Sequence-to-sequence deep neural network with spatio-spectro and temporal features for motor imagery classification
    Rammy, Sadaqat Ali
    Abbas, Waseem
    Mahmood, Syed Shahid
    Riaz, Haider
    Rehman, Haseeb Ur
    Ul Abideen, Rao Zain
    Aqeel, Muhammad
    Zhang, Wu
    BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2021, 41 (01) : 97 - 110
  • [43] Deep Spatio-Temporal Attention-Based Recurrent Network From Dynamic Adaptive Functional Connectivity for MCI Identification
    Huang, Huifang
    Liu, Qian
    Jiang, Yiqiao
    Yang, Qingyu
    Zhu, Xiaofeng
    Li, Yang
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2022, 30 : 2600 - 2612
  • [44] Modeling Temporal Dynamics with Function Approximation in Deep Spatio-Temporal Inference Network
    Karnowski, Thomas P.
    Arel, Itamar
    Young, Steven
    BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES 2011, 2011, 233 : 174 - +
  • [45] Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning
    Mozafari, Mohsen
    Law, Andrew J.
    Goubran, Rafik A.
    Green, James R.
    SENSORS, 2024, 24 (19)
  • [46] Interactive spatio-temporal feature learning network for video foreground detection
    Hongrui Zhang
    Huan Li
    Complex & Intelligent Systems, 2022, 8 : 4251 - 4263
  • [47] Attention Embedded Spatio-Temporal Network for Video Salient Object Detection
    Huang, Lili
    Yan, Pengxiang
    Li, Guanbin
    Wang, Qing
    Lin, Liang
    IEEE ACCESS, 2019, 7 : 166203 - 166213
  • [48] Video Super-Resolution via a Spatio-Temporal Alignment Network
    Wen, Weilei
    Ren, Wenqi
    Shi, Yinghuan
    Nie, Yunfeng
    Zhang, Jingang
    Cao, Xiaochun
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 1761 - 1773
  • [49] A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
    Avvenuti, Marco
    Bongiovanni, Marco
    Ciampi, Luca
    Falchi, Fabrizio
    Gennaro, Claudio
    Messina, Nicola
    2022 27TH IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS (IEEE ISCC 2022), 2022,
  • [50] Video spatio-temporal generative adversarial network for local action generation
    Liu, Xuejun
    Guo, Jiacheng
    Cui, Zhongji
    Liu, Ling
    Yan, Yong
    Sha, Yun
    JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (05)