TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Real-world Anomaly Detection in Surveillance Videos

Real-world Anomaly Detection in Surveillance Videos

Waqas Sultani, Chen Chen, Mubarak Shah

2018-01-12CVPR 2018 6Anomaly Detection In Surveillance VideosAbnormal Event Detection In VideoSemi-supervised Anomaly DetectionWeakly-supervised Video Anomaly DetectionMultiple Instance LearningAnomaly DetectionActivity Recognition
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCode

Abstract

Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at video-level instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training. We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work. The dataset is available at: https://webpages.uncc.edu/cchen62/dataset.html

Results

TaskDatasetMetricValueModel
Video UnderstandingUCF-CrimeDecidability0.613Sultani et al.
Video UnderstandingUCF-CrimeEER0.353Sultani et al.
Video UnderstandingUCF-CrimeROC AUC75.41Sultani et al.
VideoUCF-CrimeDecidability0.613Sultani et al.
VideoUCF-CrimeEER0.353Sultani et al.
VideoUCF-CrimeROC AUC75.41Sultani et al.
Anomaly DetectionUBnormalRBDC0.002MIL
Anomaly DetectionUBnormalTBDC0.001MIL
Anomaly DetectionUCF-CrimeDecidability0.613Sultani et al.
Anomaly DetectionUCF-CrimeEER0.353Sultani et al.
Anomaly DetectionUCF-CrimeROC AUC75.41Sultani et al.
Anomaly DetectionUBnormalAUC-ROC54.12MIL-Rank
Anomaly DetectionShanghaiTech Weakly SupervisedAUC-ROC85.33MIL-Rank
Anomaly DetectionShanghaiTech Weakly SupervisedFAR-Normal0.15MIL-Rank
Anomaly DetectionUBI-FightsAUC0.892Sultani et al.
Anomaly DetectionUBI-FightsDecidability0.804Sultani et al.
Anomaly DetectionUBI-FightsEER0.186Sultani et al.
Anomaly DetectionUBI-FightsAUC0.787Sultani et al.
Anomaly DetectionUBI-FightsDecidability0.738Sultani et al.
Anomaly DetectionUBI-FightsEER0.294Sultani et al.
Abnormal Event Detection In VideoUBI-FightsAUC0.892Sultani et al.
Abnormal Event Detection In VideoUBI-FightsDecidability0.804Sultani et al.
Abnormal Event Detection In VideoUBI-FightsEER0.186Sultani et al.
Abnormal Event Detection In VideoUBI-FightsAUC0.787Sultani et al.
Abnormal Event Detection In VideoUBI-FightsDecidability0.738Sultani et al.
Abnormal Event Detection In VideoUBI-FightsEER0.294Sultani et al.
Semi-supervised Anomaly DetectionUBI-FightsAUC0.787Sultani et al.
Semi-supervised Anomaly DetectionUBI-FightsDecidability0.738Sultani et al.
Semi-supervised Anomaly DetectionUBI-FightsEER0.294Sultani et al.
3D Anomaly DetectionUBnormalAUC-ROC54.12MIL-Rank
3D Anomaly DetectionShanghaiTech Weakly SupervisedAUC-ROC85.33MIL-Rank
3D Anomaly DetectionShanghaiTech Weakly SupervisedFAR-Normal0.15MIL-Rank
Video Anomaly DetectionUBnormalAUC-ROC54.12MIL-Rank
Video Anomaly DetectionShanghaiTech Weakly SupervisedAUC-ROC85.33MIL-Rank
Video Anomaly DetectionShanghaiTech Weakly SupervisedFAR-Normal0.15MIL-Rank

Related Papers

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems2025-07-213DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering2025-07-17A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys2025-07-17A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy2025-07-16Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection2025-07-15ZKP-FedEval: Verifiable and Privacy-Preserving Federated Evaluation using Zero-Knowledge Proofs2025-07-15Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers2025-07-12Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects2025-07-10