HyperAIHyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Anomaly Detection In Surveillance Videos On

평가 지표

Decidability
EER
ROC AUC

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Decidability
EER
ROC AUC
Paper TitleRepository
GMM-based0.8850.30275.90Weakly and Partially Supervised Learning Frameworks for Anomaly Detection
CR-UNet--85.24Contrastive-Regularized U-Net for Video Anomaly Detection-
STEAD-Fast--88.87STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications-
MULDE-frame-centric-micro-one-class-classification--78.5%MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection-
STEAD-Base--91.34STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications-
Multi-stream Network with Late Fuzzy Fusion--84.48A multi-stream deep neural network with late fuzzy fusion for real-world anomaly detection-
MGFN--86.98MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection-
MIST--82.30MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection-
Sultani et al.0.6130.35375.41Real-world Anomaly Detection in Surveillance Videos-
MILR--76.673D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos-
PEL--86.76Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection-
RTFM--84.03Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning-
S3R--85.99Self-supervised Sparse Representation for Video Anomaly Detection
Multiple-Instance-Based-Video-Anomaly-Detection-Using-Deep-Temporal-Encoding-Decoding--80.10Multiple Instance-Based Video Anomaly Detection using Deep Temporal Encoding-Decoding-
BN-WVAD--87.24BatchNorm-based Weakly Supervised Video Anomaly Detection-
DMRMs--81.91Anomalous Event Recognition in Videos Based on Joint Learningof Motion and Appearance with Multiple Ranking Measures-
WSAL--85.38Localizing Anomalies from Weakly-Labeled Videos-
0 of 17 row(s) selected.