# Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillance

arXiv: https://arxiv.org/abs/2509.13210 · HTML: https://mlsanity.com/paper/2509.13210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [Learning to Detect Violent Videos using Convolutional Long Short-Term Memory](https://mlsanity.com/paper/1709.06531/) (2017)
- [GhostNetV3: Exploring the Training Strategies for Compact Models](https://mlsanity.com/paper/2404.11202/) (2024)
- [Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM](https://mlsanity.com/paper/2102.10590/) (2021)

## Abstract (arXiv)

Violence detection in public surveillance is critical for public safety. This study addresses challenges such as small-scale targets, complex environments, and real-time temporal analysis. We propose Vi-SAFE, a spatial-temporal framework that integrates an enhanced YOLOv8 with a Temporal Segment Network (TSN) for video surveillance. The YOLOv8 model is optimized with GhostNetV3 as a lightweight backbone, an exponential moving average (EMA) attention mechanism, and pruning to reduce computational cost while maintaining accuracy. YOLOv8 and TSN are trained separately on pedestrian and violence datasets, where YOLOv8 extracts human regions and TSN performs binary classification of violent behavior. Experiments on the RWF-2000 dataset show that Vi-SAFE achieves an accuracy of 0.88, surpassing TSN alone (0.77) and outperforming existing methods in both accuracy and efficiency, demonstrating its effectiveness for public safety surveillance. Code is available at https://anonymous.4open.science/r/Vi-SAFE-3B42/README.md.