XAVAD：面向匿名化人群视频监控的零样本异常解释方法
Guided Zero-Shot Anomaly Explanation for Anonymized Crowd Video Monitoring: Context, Categorization, and Spatial Localization
AI 导读
研究者提出 XAVAD 方法，为匿名化视频异常检测（VAD）提供统一的描述性 XAI 解释，整合零样本匿名化、异常类型分类、空间定位与场景上下文描述。该方法采用多模态 CLIP 视频嵌入、LLM 辅助提示词与 pool-scoring 机制识别异常类型，并增强 Grad-ECLIP 实现异常热图定位，用 VLM 生成上下文与推理描述。
正文 · 原文
Abstract:Despite the promising development of deep learning for video anomaly detection (VAD), explainability (XAI) of these models remains a challenge. Explainable and privacy-protecting VAD builds transparency and trust that facilitates adoption of computer vision systems, including safety and security monitoring. However, anomaly explainability in privacy-preserving VAD systems is underexplored. In this study, we present the XAVAD approach, a unified descriptive anomaly XAI for an anonymized VAD, that integrates flexible zero-shot anonymization, anomaly type categorization, visual localization, and scene context description. We provide empirical and qualitative assessments of multifaceted explanations integrated with full-body visual anonymization for privacy protection. We adopt a multimodal CLIP embedding for videos, using improved LLM-assisted prompting and pool-scoring mechanisms for anomaly-type identification. We enhance Grad-ECLIP for spatial anomaly heatmap localization, leveraging computation and accuracy through our novel prompt-guided patching autofocus mechanism. We employ VLMs to generate context and reasoning descriptions of detected anomalies through curated prompt engineering. We have evaluated the accuracy and computational cost of XAVAD on several publicly available CCTV and video datasets. Our experiments demonstrate substantial gains of our XAVAD over state-of-the-art benchmark approaches and provide insights into privacy protection trade-offs in XAI for VAD. We further present ablation studies and assessments across diverse configurations and modeling alternatives to demonstrate the efficacy of our proposed methods. Code: this https URL}{this https URL .
| Comments: | 21 pages, 12 figures, 13 tables, preprint |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32073 [cs.CV] |
| (or arXiv:2610.32073v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32073 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mulugeta Weldezgina Asres [view email]
[v1]
Fri, 23 Oct 2026 02:19:42 UTC (14,400 KB)
来源：arXiv cs.AI · arxiv.org