Lightweight Vision Transformer with CBAM and LSTM for Efficient Violence Detection in Image Sequences

Garg, Aishvarya

doi:10.1007/s11760-026-05207-7

Lightweight Vision Transformer with CBAM and LSTM for Efficient Violence Detection in Image Sequences

2026-03-31

1

PRE

AI

G

Garg, Aishvarya

N

Nigam, Swati

S

Singh, Rajiv *

DOI：10.1007/s11760-026-05207-7

Original

Original request for help

Save

Abstract

En 中文

In recent years, the need for efficient violence detection methods has become increasingly critical for various security applications. Existing approaches leveraging deep learning (DL), particularly Vision Transformers (ViTs), often suffer from high complexity and overhead, limiting their real-time applicability. This paper proposes a lightweight spatiotemporal transformer-based violence detection method that integrates ViT with a Convolutional Block Attention Module (CBAM) and Long Short-Term Memory (LSTM) for spatial and temporal feature extraction, respectively. By replacing the multi-head self-attention (MSA) mechanism in ViT with CBAM, we significantly reduce the number of parameters and computational costs while enhancing the model's ability to focus on localized patterns essential for violence detection. Our approach is validated on four benchmark datasets, achieving accuracies of 99.81%, 99%, 99.50%, and 99.10% on AIRTLab, Industrial Surveillance, RWF2000, and Hockey Fights, respectively. The proposed method demonstrates a good balance between model complexity and computational efficiency, making it suitable for real-time violence detection applications.

Keywords:

CBAM

Deep learning

LSTM

Violence detection

ViT

Lightweight Vision Transformer with CBAM and LSTM for Efficient Violence Detection in Image Sequences

Abstract

Journal

Organization

Cited Papers

Citing Papers