通过上下文记忆实现实时视频异常检测，提升零样本泛化能力。
TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection
- 用跨注意力融合时序信号与视觉嵌入，构建带记忆的检测流程。
- 在UCF-Crime上达90.4% AUC，XD-Violence上83.67% AP，刷新零样本纪录。
- 适合真实场景监控部署，具备高精度与可解释性优势。
视频异常往往依赖上下文信息和时间演化。同一行为在不同上下文中可能正常或异常。现有检测器普遍忽略上下文，严重限制其在新场景下的泛化能力。本文针对上下文感知的零样本异常检测挑战，提出一种实时记忆增强型检测框架：通过交叉注意力将时序信号与视觉嵌入关联，并利用上下文相似度评分实现零样本异常分类。模型在UCF-Crime上达到90.4% AUC，XD-Violence上达83.67% AP，为当前零样本模型最优表现。系统支持实时推理，兼具高精度与可解释性，验证了融合交叉注意力时序融合与上下文记忆的有效性，推动零样本模型在真实监控场景中的应用落地。
原文摘要 · Abstract (English)
Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which seriously limits their capability to generalize to new, real-life situations. Our work addresses the context-aware zero-shot anomaly detection challenge, in which systems need to learn adaptively to detect new events by correlating temporal and appearance features with textual traces of memory in real time. Our approach defines a memory-augmented pipeline, correlating temporal signals with visual embeddings using cross-attention, and real-time zero-shot anomaly classification by contextual similarity scoring. We achieve 90.4\% AUC on UCF-Crime and 83.67\% AP on XD-Violence, a new state-of-the-art among zero-shot models. Our model achieves real-time inference with high precision and explainability for deployment. We show that, by fusing cross-attention temporal fusion and contextual memory, we achieve high fidelity anomaly detection, a step towards the applicability of zero-shot models in real-world surveillance and infrastructure monitoring.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。