arXiv 2508.184632025-08-27cs.CVcs.LG

基于对比与预测时空建模的监控场景上下文感知零样本异常检测

Context-Aware Zero-Shot Anomaly Detection in Surveillance Using Contrastive and Predictive Spatiotemporal Modeling

Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh（计算机科学与工程系，BRAC大学，达卡，孟加拉国）

Md. Rashid Shahriar Khan, Md. Abrar Hasan, Mohammod Tareq Aziz Justice

备注：: 11 pages, 7 figures, 4 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种结合 TimeSformer、DPC 与 CLIP 的上下文感知零样本异常检测框架，通过时空预测建模和视觉-语言语义理解，在无需异常样本训练的情况下实现监控视频中的异常识别。

摘要：

在监控视频中检测异常本质上具有挑战性，因为异常事件具有不可预测性和上下文依赖性。本文提出了一种新颖的上下文感知零样本异常检测框架，该框架在训练过程中无需接触任何异常样本即可识别异常事件。所提出的混合架构结合了 TimeSformer、DPC 和 CLIP，用于建模时空动态和语义上下文。TimeSformer 作为视觉骨干网络提取丰富的时空特征，而 DPC 通过预测未来表示来识别时间偏差。此外，基于 CLIP 的语义流通过上下文特定的文本提示实现概念级异常检测。这些组件使用 InfoNCE 和 CPC 损失进行联合训练，将视觉输入与其时间和语义表示对齐。上下文门控机制通过利用场景感知线索或全局视频特征来调制预测，进一步增强决策能力。通过将预测建模与视觉-语言理解相结合，该系统能够泛化到复杂环境中未见过的行为。该框架弥合了监控场景零样本异常检测中时间推理与语义上下文之间的差距。本研究的代码已在 https://github.com/NK-II/Context-Aware-Zero-Shot-Anomaly-Detection-in-Surveillance 公开。

英文摘要：

Detecting anomalies in surveillance footage is inherently challenging due to their unpredictable and context-dependent nature. This work introduces a novel context-aware zero-shot anomaly detection framework that identifies abnormal events without exposure to anomaly examples during training. The proposed hybrid architecture combines TimeSformer, DPC, and CLIP to model spatiotemporal dynamics and semantic context. TimeSformer serves as the vision backbone to extract rich spatial-temporal features, while DPC forecasts future representations to identify temporal deviations. Furthermore, a CLIP-based semantic stream enables concept-level anomaly detection through context-specific text prompts. These components are jointly trained using InfoNCE and CPC losses, aligning visual inputs with their temporal and semantic representations. A context-gating mechanism further enhances decision-making by modulating predictions with scene-aware cues or global video features. By integrating predictive modeling with vision-language understanding, the system can generalize to previously unseen behaviors in complex environments. This framework bridges the gap between temporal reasoning and semantic context in zero-shot anomaly detection for surveillance. The code for this research has been made available at https://github.com/NK-II/Context-Aware-Zero-Shot-Anomaly-Detection-in-Surveillance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。