Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Anomaly Detection On Ucsd Ped2

Metrics

AUC

Results

Performance results of various models on this benchmark

Model Name	AUC	Paper Title	Repository
Two-stream	97.1%	Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
Background-Agnostic	98.7%	A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
STPT	98.9%	Spatio-temporal predictive tasks for abnormal event detection in videos	-
DMAD	99.7%	Diversity-Measurable Anomaly Detection
SD-MAE	95.4%	Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
MAMA	98.2%	Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer
VALD-GAN	97.74	VALD-GAN: video anomaly detection using latent discriminator augmented GAN	-
ASTNet	97.4%	Attention-based residual autoencoder for video anomaly detection
FastAno	96.3%	FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation
STemGAN	97.5	STemGAN: spatio-temporal generative adversarial network for video anomaly detection	-
AnomalyRuler	97.9%	Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
MULDE-object-centric-micro	99.7%	MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
ConvVQ	90.2%	Diversity-Measurable Anomaly Detection

0 of 13 row(s) selected.