Video anomaly detection with NTCN-ML: A novel TCN for multi-instance learning - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Année : 2023

Video anomaly detection with NTCN-ML: A novel TCN for multi-instance learning

Résumé

A key challenge in video anomaly detection is the identification of rare abnormal patterns in the positive instances as they exhibit only a small variation compared to normal patterns, and they are largely biased by the dominant negative instances. To address this issue, we propose a weakly supervised video anomaly detection model called NTCN-ML - Novel Temporal Convolutional Network Multi-Instance Learning Model. The NTCN-ML model extracts temporal representations of video data to construct a time-series pattern to optimize the multi-instance learning process. The model examines the correlation between positive and negative samples in the multi-instance learning process to balance the feature association between rare positive and negative instances. The video anomaly detection with the NTCN-ML model achieved 95.3\% and 85.1\% accuracy for UCF-Crime and ShanghaiTech datasets, respectively, and outperformed the baseline models.
Fichier principal
Vignette du fichier
PR-D-23-00012_clean_version.pdf (4.58 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04131687 , version 1 (16-06-2023)

Identifiants

Citer

Wenhao Shao, Ruliang Xiao, Praboda Rajapaksha, Mengzhu Wang, Zhigang Luo, et al.. Video anomaly detection with NTCN-ML: A novel TCN for multi-instance learning. Pattern Recognition, 2023, 143, pp.109765. ⟨10.1016/j.patcog.2023.109765⟩. ⟨hal-04131687⟩
24 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More