Video violence recognition based on deep learning concerns accurate yet
scalable human violence recognition. Currently, most state-of-the-art video
violence recognition studies use CNN-based models to represent and categorize
videos. However, recent studies suggest that pre-trained transformers are more
accurate than CNN-based models on various video analysis benchmarks. Yet these
models are not thoroughly evaluated for video violence recognition. This paper
introduces a novel transformer-based Mixture of Experts (MoE) video violence
recognition system. Through an intelligent combination of large vision
transformers and efficient transformer architectures, the proposed system not
only takes advantage of the vision transformer architecture but also reduces
the cost of utilizing large vision transformers. The proposed architecture
maximizes violence recognition system accuracy while actively reducing
computational costs through a reinforcement learning-based router. The
empirical results show the proposed MoE architecture's superiority over
CNN-based models by achieving 92.4% accuracy on the RWF dataset.

基于深度学习的视频暴力识别研究了准确且可扩展的人类暴力识别问题。本文提出了一种基于 Transformer 的新型专家混合 (MoE) 视频暴力识别系统，通过智能组合大型视觉 Transformer 和高效 Transformer 结构，系统不仅充分利用了视觉 Transformer 架构，还降低了使用大型视觉 Transformer 的成本。通过强化学习路由器，该架构最大化了暴力识别系统的准确性，并积极降低了计算成本。实证结果显示，在 RWF 数据集上，所提出的 MoE 架构相较于基于 CNN 的模型具有卓越的 92.4% 准确率。