Semi Supervised Anomaly Detection On Ubi
Métriques
AUC
Decidability
EER
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | AUC | Decidability | EER | Paper Title | Repository |
|---|---|---|---|---|---|
| Hasan et al. | 0.528 | 0.194 | 0.466 | Learning Temporal Regularity in Video Sequences | |
| LSTM-AE | 0.541 | 0.059 | 0.480 | Abnormal Event Detection in Videos using Spatiotemporal Autoencoder | |
| SS-Model + WS-Model + Sultani et al. | 0.846 | 1.108 | 0.216 | Iterative weak/self-supervised classification framework for abnormal events detection | |
| s2-VAE | 0.540 | 0.164 | 0.475 | Generative Neural Networks for Anomaly Detection in Crowded Scenes | |
| Sultani et al. | 0.787 | 0.738 | 0.294 | Real-world Anomaly Detection in Surveillance Videos | |
| SS-Model | 0.819 | 0.986 | 0.284 | Iterative weak/self-supervised classification framework for abnormal events detection | |
| Adversarial Generator | 0.533 | 0.147 | 0.484 | Abnormal Event Detection in Videos using Generative Adversarial Nets | - |
0 of 7 row(s) selected.