Home / Advanced Search

  • Title/Keywords

  • Author/Affliations

  • Journal

  • Article Type

  • Start Year

  • End Year

Update SearchingClear
  • Articles
  • Online
Search Results (2)
  • Open Access

    ARTICLE

    Leveraging Federated Learning for Efficient Privacy-Enhancing Violent Activity Recognition from Videos

    Moshiur Rahman Tonmoy1, Md. Mithun Hossain1, Mejdl Safran2,*, Sultan Alfarhood2, Dunren Che3, M. F. Mridha4

    CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5747-5763, 2025, DOI:10.32604/cmc.2025.067589 - 23 October 2025

    Abstract Automated recognition of violent activities from videos is vital for public safety, but often raises significant privacy concerns due to the sensitive nature of the footage. Moreover, resource constraints often hinder the deployment of deep learning-based complex video classification models on edge devices. With this motivation, this study aims to investigate an effective violent activity classifier while minimizing computational complexity, attaining competitive performance, and mitigating user data privacy concerns. We present a lightweight deep learning architecture with fewer parameters for efficient violent activity recognition. We utilize a two-stream formation of 3D depthwise separable convolution coupled More >

  • Open Access

    ARTICLE

    Anomaly Based Camera Prioritization in Large Scale Surveillance Networks

    Altaf Hussain1,2, Khan Muhammad1, Hayat Ullah1, Amin Ullah1,4, Ali Shariq Imran3, Mi Young Lee1, Seungmin Rho1, Muhammad Sajjad2,3,*

    CMC-Computers, Materials & Continua, Vol.70, No.2, pp. 2171-2190, 2022, DOI:10.32604/cmc.2022.018181 - 27 September 2021

    Abstract Digital surveillance systems are ubiquitous and continuously generate massive amounts of data, and manual monitoring is required in order to recognise human activities in public areas. Intelligent surveillance systems that can automatically ide.pngy normal and abnormal activities are highly desirable, as these would allow for efficient monitoring by selecting only those camera feeds in which abnormal activities are occurring. This paper proposes an energy-efficient camera prioritisation framework that intelligently adjusts the priority of cameras in a vast surveillance network using feedback from the activity recognition system. The proposed system addresses the limitations of existing manual… More >

Displaying 1-10 on page 1 of 2. Per Page