Scholarlink

<p>We propose Adaptive Late Router with Temperature Scaling (ALeRT), an inference-only, disagreement-aware late fusion framework for clip-level video anomaly detection. ALeRT combines two complementary experts: MMAnet, a lightweight multi-scale 3D CNN for fine-grained motion dynamics, and MViT, a Kinetics-pretrained multiscale Vision Transformer for long-range spatiotemporal modeling, without requiring joint retraining. Model outputs are calibrated using temperature scaling and fused via a Product-of-Experts (PoE) to reinforce agreement, while disagreement is resolved using confidence margins and per-class Positive Predictive Value (PPV). Temporal consistency is further enhanced through exponential moving average (EMA) smoothing. The framework is evaluated across multiple random seeds, reporting mean performance with low variance, demonstrating strong robustness and generalization. Experiments on LPS ( Loss Preventive Surveillance), UCF-Crime-Clips (UCF-CC), and Virat2-RC (ReClassified) datasets show consistent improvements over individual backbones. Notably, ALeRT achieves these gains with only <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\sim \)</EquationSource> </InlineEquation>3.1 ms fusion overhead per clip, enabling real-time inference (5.7–6.0 events/s, maximum of 300 FPS(FPS (frames per second) indicates the number of video frames processed per second.)) on commodity GPUs. These results highlight the effectiveness of disagreement-aware fusion for scalable and deployment-ready video anomaly detection.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Disagreement-aware late fusion of 3DCNN and MViT for clip-level video anomaly detection

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月30日

查看全文
  • K. Mohanarangan,
  • P. Palanisamy

摘要

We propose Adaptive Late Router with Temperature Scaling (ALeRT), an inference-only, disagreement-aware late fusion framework for clip-level video anomaly detection. ALeRT combines two complementary experts: MMAnet, a lightweight multi-scale 3D CNN for fine-grained motion dynamics, and MViT, a Kinetics-pretrained multiscale Vision Transformer for long-range spatiotemporal modeling, without requiring joint retraining. Model outputs are calibrated using temperature scaling and fused via a Product-of-Experts (PoE) to reinforce agreement, while disagreement is resolved using confidence margins and per-class Positive Predictive Value (PPV). Temporal consistency is further enhanced through exponential moving average (EMA) smoothing. The framework is evaluated across multiple random seeds, reporting mean performance with low variance, demonstrating strong robustness and generalization. Experiments on LPS ( Loss Preventive Surveillance), UCF-Crime-Clips (UCF-CC), and Virat2-RC (ReClassified) datasets show consistent improvements over individual backbones. Notably, ALeRT achieves these gains with only \(\sim \) 3.1 ms fusion overhead per clip, enabling real-time inference (5.7–6.0 events/s, maximum of 300 FPS(FPS (frames per second) indicates the number of video frames processed per second.)) on commodity GPUs. These results highlight the effectiveness of disagreement-aware fusion for scalable and deployment-ready video anomaly detection.