Anomaly Detection On Chuk Avenue

Metrics

AUC

RBDC

TBDC

Results

Performance results of various models on this benchmark

Model Name	AUC	RBDC	TBDC	Paper Title	Repository
SSMTL+UBnormal	93.0%	61.10	61.38	UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
Sparse Coding Stacked RNN	81.7%	-	-	A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework
ASTNet	86.7%	-	-	Attention-based residual autoencoder for video anomaly detection
Narrowed Normality Clusters	88.9%	-	-	Detecting abnormal events in video using Narrowed Normality Clusters	-
Appearance-Motion Correspondence	86.9%	-	-	Anomaly Detection in Video Sequence with Appearance-Motion Correspondence	-
HF2VAD+SSPCAB	-	-	89.28	Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
ConvVQ	84.3%	-	-	Diversity-Measurable Anomaly Detection
Background- Agnostic Framework+SSPCAB	92.9%	65.99	-	Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
Siamese Net	87.2%	41.20	78.60	Learning a distance function with a Siamese network to localize anomalies in videos	-
Cloze Test	89.6%	-	-	Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events
Future Frame Prediction	85.1%	19.59	56.01	Future Frame Prediction for Anomaly Detection -- A New Baseline
VALD-GAN	91.03	-	-	VALD-GAN: video anomaly detection using latent discriminator augmented GAN	-
SSMTL++v2	91.6%	47.8	85.2	-	-
FastAno	85.3%	-	-	FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation
Learning not to reconstruct	87.1%	-	-	Learning Not to Reconstruct Anomalies
MULDE-object-centric-micro	94.3%	-	-	MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
MAMA	91.2%	-	-	Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer
VideoPatchCore	92.8%	-	-	VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection
PGM	92.72%	60.18	72.09	Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified
AMSRC	93.8%	-	-	A Video Anomaly Detection Framework based on Appearance-Motion Semantics Representation Consistency	-

0 of 35 row(s) selected.