SOTAVerified

Anomaly Detection In Surveillance Videos

"The goal of a practical anomaly detection system is to timely signal an activity that deviates normal patterns and identify the time window of the occurring anomaly. [It] can be considered as coarse level video understanding, which filters out anomalies from normal patterns." A critical task in video surveillance is detecting anomalous events such as traffic accidents, crimes or illegal activities. Anomalous events rarely occur as compared to normal activities. Hence the application of this task is to "alleviate the waste of labor and time, developing intelligent computer vision algorithms for automatic video anomaly detection".

(Credit: Real-world Anomaly Detection in Surveillance Videos)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 66 papers

TitleStatusHype
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly DetectionCode2
Normalizing Flows for Human Pose Anomaly DetectionCode1
Dual‑detector Re‑optimization for Federated Weakly Supervised Video Anomaly Detection Via Adaptive Dynamic Recursive MappingCode1
ADNet: Temporal Anomaly Detection in Surveillance VideosCode1
MIST: Multiple Instance Self-Training Framework for Video Anomaly DetectionCode1
MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly DetectionCode1
FastAno: Fast Anomaly Detection via Spatio-temporal Patch TransformationCode1
Iterative weak/self-supervised classification framework for abnormal events detectionCode1
Audio-Guided Attention Network for Weakly Supervised Violence DetectionCode1
Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence DetectionCode1
Localizing Anomalies from Weakly-Labeled VideosCode1
Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic SpaceCode1
Anomaly Detection in Video via Self-Supervised and Multi-Task LearningCode1
Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection MethodCode1
MIST: Multiple Instance Spatial Transformer NetworkCode1
Diversity-Measurable Anomaly DetectionCode1
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in VideoCode1
Attention-based residual autoencoder for video anomaly detectionCode1
Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence DetectionCode1
BatchNorm-based Weakly Supervised Video Anomaly DetectionCode1
Consistency-based Self-supervised Learning for Temporal Anomaly LocalizationCode1
Anomaly detection in surveillance videos using transformer based attention modelCode1
Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly DetectionCode1
Learning Memory-guided Normality for Anomaly DetectionCode1
Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak SupervisionCode1
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.