Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Senadeera, Damith Chamalke, Yang, Xiaoyun, Li, Shibo, Awais, Muhammad, Kollias, Dimitrios, Slabaugh, Gregory
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918148121296896
author Senadeera, Damith Chamalke
Yang, Xiaoyun
Li, Shibo
Awais, Muhammad
Kollias, Dimitrios
Slabaugh, Gregory
author_facet Senadeera, Damith Chamalke
Yang, Xiaoyun
Li, Shibo
Awais, Muhammad
Kollias, Dimitrios
Slabaugh, Gregory
contents The rapid proliferation of surveillance cameras has increased the demand for automated violence detection. While CNNs and Transformers have shown success in extracting spatio-temporal features, they struggle with long-term dependencies and computational efficiency. We propose Dual Branch VideoMamba with Gated Class Token Fusion (GCTF), an efficient architecture combining a dual-branch design and a state-space model (SSM) backbone where one branch captures spatial features, while the other focuses on temporal dynamics. The model performs continuous fusion via a gating mechanism between the branches to enhance the model's ability to detect violent activities even in challenging surveillance scenarios. We also present a new benchmark by merging RWF-2000, RLVS, SURV and VioPeru datasets in video violence detection, ensuring strict separation between training and testing sets. Experimental results demonstrate that our model achieves state-of-the-art performance on this benchmark and also on DVD dataset which is another novel dataset on video violence detection, offering an optimal balance between accuracy and computational efficiency, demonstrating the promise of SSMs for scalable, near real-time surveillance violence detection.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03162
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection
Senadeera, Damith Chamalke
Yang, Xiaoyun
Li, Shibo
Awais, Muhammad
Kollias, Dimitrios
Slabaugh, Gregory
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
The rapid proliferation of surveillance cameras has increased the demand for automated violence detection. While CNNs and Transformers have shown success in extracting spatio-temporal features, they struggle with long-term dependencies and computational efficiency. We propose Dual Branch VideoMamba with Gated Class Token Fusion (GCTF), an efficient architecture combining a dual-branch design and a state-space model (SSM) backbone where one branch captures spatial features, while the other focuses on temporal dynamics. The model performs continuous fusion via a gating mechanism between the branches to enhance the model's ability to detect violent activities even in challenging surveillance scenarios. We also present a new benchmark by merging RWF-2000, RLVS, SURV and VioPeru datasets in video violence detection, ensuring strict separation between training and testing sets. Experimental results demonstrate that our model achieves state-of-the-art performance on this benchmark and also on DVD dataset which is another novel dataset on video violence detection, offering an optimal balance between accuracy and computational efficiency, demonstrating the promise of SSMs for scalable, near real-time surveillance violence detection.
title Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.03162