Video anomaly detection under video-level labels is currently a challenging task. Previous works have made progresses on discriminating whether a video sequencecontains anomalies. However, most of them fail to accurately localize the anomalous events within videos in the temporal domain. In this paper, we propose a Weakly Supervised Anomaly Localization (WSAL) method focusing on temporally localizing anomalous segments within anomalous videos. Inspired by the appearance difference in anomalous videos, the evolution of adjacent temporal segments is evaluated for the localization of anomalous segments. To this end, a high-order context encoding model is proposed to not only extract semantic representations but also measure the dynamic variations so that the temporal context could be effectively utilized. In addition, in order to fully utilize the spatial context information, the immediate semantics are directly derived from the segment representations. The dynamic variations as well as the immediate semantics, are efficiently aggregated to obtain the final anomaly scores. An enhancement strategy is further proposed to deal with noise interference and the absence of localization guidance in anomaly detection. Moreover, to facilitate the diversity requirement for anomaly detection benchmarks, we also collect a new traffic anomaly (TAD) dataset which specifies in the traffic conditions, differing greatly from the current popular anomaly detection evaluation benchmarks.Extensive experiments are conducted to verify the effectiveness of different components, and our proposed method achieves new state-of-the-art performance on the UCF-Crime and TAD datasets.
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；The University of Adelaide（阿德莱德大学）；Advanced Analytics Institute（高级分析研究所）；University of Technology Sydney（悉尼科技大学）
VERIDAH: Solving Enumeration Anomaly Aware Vertebra Labeling across Imaging Sequences
TUM University Hospital（慕尼黑技术大学医院）；Technical University of Munich (TUM)（慕尼黑技术大学）；Institute of Biomedical Engineering（生物医学工程学院）；Polytechnique Montreal（蒙特利尔理工学院）；Mila -- Quebec AI Institute（魁北克人工智能研究所）；University of Zurich（苏黎世大学）；Rostock University Medical Center（罗斯托克大学医学中心）；University Hospital Heidelberg（海德堡大学医院）；Medical Center -- University of Freiburg（弗赖堡大学医学中心）；Max-Delbrueck-Center for Molecular Medicine in the Helmholtz Association (MDC)（马克斯-德尔布吕克分子医学中心（马克斯·普朗克协会））；University Hospital Augsburg（奥格斯堡大学医院）
SimpleNet: A Simple Network for Image Anomaly Detection and Localization
University of Science Technology of China（中国科学技术大学）；Meka Technology Co Ltd（美卡科技有限公司）
我们提出了一个简单的和应用程序友好的网络（称为SimpleNet）检测和定位异常。SimpleNet由四个组件组成：（1）一个预训练的特征提取器，用于生成局部特征;（2）一个浅层特征适配器，用于将局部特征转移到目标域;（3）一个简单的异常特征生成器，通过向正常特征添加高斯噪声来伪造异常特征;以及（4）一个二进制异常鉴别器，用于区分异常特征和正常特征。在推理过程中，异常特征生成器将被丢弃。我们的方法基于三个直觉。首先，将预先训练的特征转换为面向目标的特征有助于避免领域偏见。其次，在特征空间中生成合成异常更有效，因为缺陷在图像空间中可能没有太多的共性。第三，一个简单的系统是非常有效和实用的。尽管简单，SimpleNet在定量和定性上优于以前的方法。在MVTec AD基准测试中，SimpleNet实现了99.6%的异常检测AUROC，与下一个表现最好的模型相比，误差减少了55.5%。此外，SimpleNet比现有方法更快，在3080 ti GPU上具有77 FPS的高帧速率。此外，SimpleNet在单类新奇检测任务的性能上有了显着的改进。代码：https://github.com/DonaldRR/SimpleNet.
VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Edinburgh（爱丁堡大学）；Khalifa University（哈利法大学）；Linköping University（林雪平大学）；Australian National University（澳大利亚国立大学）
A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection
Tongji University（同济大学）；Huaiyin Normal University（淮阴师范学院）；Jiangsu Province Engineering Research Center for Intelligent Monitoring and Management of Small Water Bodies（江苏省小型水体智能监测与管理工程研究中心）
EventVAD: Training-Free Event-Aware Video Anomaly Detection
Peking University（北京大学）；Guangdong University of Technology（广东工业大学）；The University of Sheffield（谢菲尔德大学）；University of Science and Technology Beijing（北京科技大学）；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Nanjing University（南京大学）；University of Trento（特伦特大学）；Queen's University Belfast（贝尔法斯特女王大学）
Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation
National Institute for Data Science in Health and Medicine, Xiamen University（厦门大学健康与医学数据科学国家研究院）；Jarvis Research Center, Tencent YouTu Lab（腾讯优图实验室贾维斯研究中心）；Westlake University（西湖大学）；The Chinese University of Hong Kong（香港中文大学）；School of Engineering, The University of Edinburgh（爱丁堡大学工程学院）
Self-supervised learning for classifying paranasal anomalies in the maxillary sinus
University Medical Center Hamburg-Eppendorf（汉堡埃彭多夫大学医学中心）；Department of Otorhinolaryngology, Head and Neck Surgery and Oncology（耳鼻喉科、头颈外科及肿瘤科）；Clinic and Polyclinic for Diagnostic and Interventional Radiology and Nuclear Medicine（诊断与介入放射学及核医学临床与门诊）；Population Health Research Department, University Heart and Vascular Center（大学心脏血管中心人群健康研究部）；Clinic and Polyclinic for Neurology（神经科临床与门诊）
Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China（计算机功率网络与信息安全重点实验室，教育部，山东计算机科学中心（济南国家超级计算机中心），齐鲁大学（山东科学院），济南，中国）；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, China（山东省计算功率互联网与服务计算重点实验室，山东省计算机科学基础研究中心，济南，中国）
Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；The Hong Kong Polytechnic University（香港理工大学）；Pazhou Lab（琶洲实验室）
Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection
Technical University of Munich（慕尼黑工业大学）；Helmholtz AI（亥姆霍兹人工智能）；Helmholtz Center Munich（亥姆霍兹慕尼黑中心）；Klinikum Rechts der Isar（伊萨尔河右岸医院）；Imperial College London（帝国理工学院）；King’s College London（伦敦国王学院）
Reconstruction-Based Anomaly Localization via Knowledge-Informed Self-Training
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）
