Video Anomaly Detection
14개 벤치마크 · 논문 346편 · 이 태스크의 논문 보기 →
Benchmarks
HR-ShanghaiTech
HR-Avenue
HR-UBnormal
ShanghaiTech
CUHK Avenue
UBnormal
ShanghaiTech Campus
UCF-Crime
UCSD Ped2
Ped2
CHAD
CHUK Avenue
IITB Corridor
Street Scene
Most implemented
Adversarially Learned One-Class Classifier for Novelty Detection
An Attribute-based Method for Video Anomaly Detection
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight
Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention
Papers
Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding
Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and curated annotations, limiting generalization in open-set scenarios. Rece…
Video Anomaly DetectionProbe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection
Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for training-free VAD, but existing approaches impose restrictive inter…
Video Anomaly DetectionAdaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection
As the scale of video surveillance data outpaces manual annotation capacities, weakly supervised video anomaly detection (WSVAD) has emerged as a critical research frontier. Most existing approaches formulate WSVAD withi…
Multiple Instance LearningVideo Anomaly DetectionEvent SegmentationA VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection
Anomaly detection aims to identify observations that deviate from normal patterns. Recent work uses pretrained vision-language models (VLMs) for training-free image and video anomaly detection without task-specific retra…
Video Anomaly DetectionSTEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection
Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving poses, recent methods train Energy-Based…
Computational EfficiencyVideo Anomaly DetectionPose EstimationRethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness
Open-world video anomaly detection (OWVAD) is expected to detect events that match a user-specified definition of abnormality. This requirement is stronger than generic anomaly localization: in the same video, changing t…
Video Anomaly Detection