OE-CTST: Outlier-Embedded Cross Temporal Scale Transformer for Weakly-supervised Video Anomaly Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

OE-CTST: Outlier-Embedded Cross Temporal Scale Transformer for Weakly-supervised Video Anomaly Detection

Rui Dai
  • Fonction : Auteur
Quan Kong
  • Fonction : Auteur
Lorenzo Garattoni
  • Fonction : Auteur
Gianpiero Francesca
  • Fonction : Auteur

Résumé

Video anomaly detection in real-world scenarios is challenging due to the complex temporal blending of long and short-length anomalies with normal ones. Further, it is more difficult to detect those due to : (i) Distinctive features characterizing the short and long anomalies with sharp and progressive temporal cues respectively; (ii) Lack of precise temporal information (i.e. weak-supervision) limits the temporal dynamics modeling of anomalies from normal events. In this paper, we propose a novel ‘temporal transformer’ framework for weakly-supervised anomaly detection: OE-CTST†. The proposed framework has two major components: (i) Outlier Embedder (OE) and (ii) Cross Temporal Scale Transformer (CTST). First, OE gen- erates anomaly-aware temporal position encoding to allow the transformer to effectively model the temporal dynamics among the anomalies and normal events. Second, CTST encodes the cross-correlation between multi-temporal scale features to benefit short and long length anomalies by modeling the global temporal relations. The proposed OE-CTST is validated on three publicly available datasets i.e. UCF-Crime, XD-Violence, and IITB-Corridor, outperforming recently reported state-of-the-art approaches.
Fichier principal
Vignette du fichier
OE_CTST__WACV__24_Application_Track_-2.pdf (1.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04516331 , version 1 (22-03-2024)

Identifiants

  • HAL Id : hal-04516331 , version 1

Citer

Snehashis Majhi, Rui Dai, Quan Kong, Lorenzo Garattoni, Gianpiero Francesca, et al.. OE-CTST: Outlier-Embedded Cross Temporal Scale Transformer for Weakly-supervised Video Anomaly Detection. WACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision, Jan 2024, Hawaii, United States. ⟨hal-04516331⟩
2 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More