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.
Towards Total Recall in Industrial Anomaly Detection
University of Tübingen（图宾根大学）；Amazon AWS（亚马逊云科技）
能够发现有缺陷的零件是大规模工业制造的关键组成部分。我们在这项工作中解决的一个特殊挑战是冷启动问题：仅使用标称（无缺陷）示例图像拟合模型。虽然每个类的手工解决方案是可能的，但目标是构建自动同时在许多不同任务上工作的系统。性能最好的方法将ImageNet模型的嵌入与离群值检测模型相结合。在本文中，我们扩展这条线的工作，并提出了\textbf{PatchCore}，它使用了最大限度地代表存储体的名义补丁功能。PatchCore提供具有竞争力的推理时间，同时实现检测和定位的最先进性能。在具有挑战性的广泛使用的MVTec AD基准测试中，PatchCore实现了高达$99.6\%$的图像级异常检测AUROC评分，与下一个最佳竞争对手相比，误差减少了一半以上。我们进一步报告了两个额外的数据集上的竞争结果，并在少数样本制度中找到了竞争结果。\freefootnote{$^*$ Work done during a research internship at Amazon AWS.}代码：github.com/amazon-research/patchcore-inspection.
Video Anomaly Detection Using Pre-Trained Deep Convolutional Neural Nets and Context Mining
NSF Center for Cloud and Autonomic Computing（NSF云与自主计算中心）；Department of Computer Science（计算机科学系）；The University of Arizona（亚利桑那大学）；The University of North Texas（北得克萨斯大学）
Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
Hanoi University of Science and Technology（河内科技大学）；University of Information Technology, VNU-HCM（胡志明市国家大学信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市国家大学）；VinUniversity；Vietnamese-German University（越南德国大学）
Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists
Hupan Lab（湖畔实验室）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The First Affiliated Hospital of College of Medicine, Zhejiang University（浙江大学医学院附属第一医院）；Guangdong Provincial People’s Hospital（广东省人民医院）
Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
