HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Anomaly Detection On Ucsd Ped2

评估指标

AUC

评测结果

各个模型在此基准测试上的表现结果

模型名称	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.