Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection

Rui Dai
Quan Kong
  • Fonction : Auteur
Lorenzo Garattoni
  • Fonction : Auteur
  • PersonId : 1120055
Gianpiero Francesca
  • Fonction : Auteur
  • PersonId : 1023188

Résumé

Video anomaly detection in surveillance systems with only video-level labels (i.e. weakly-supervised) is challenging. This is due to, (i) complex integration of human and scene based anomalies comprising of subtle and sharp spatio-temporal cues in real-world scenarios, (ii) non-optimal optimization between normal and anomaly instances under weak-supervision. In this paper, we propose a Human-Scene Network to learn discriminative representations by capturing both subtle and strong cues in a dissociative manner. In addition, a self-rectifying loss is also proposed that dynamically computes the pseudo temporal-annotations from video-level labels for optimizing the Human-Scene Network effectively. The proposed Human-Scene Network optimized with self-rectifying loss is validated on three publicly available datasets i.e. UCF-Crime, ShanghaiTech and IITB-Corridor, outperforming recently reported state-of-the-art approaches on five out of the six scenarios considered.
Fichier principal
Vignette du fichier
HSN.pdf (380.74 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03946181 , version 1 (19-01-2023)

Identifiants

  • HAL Id : hal-03946181 , version 1

Citer

Snehashis Majhi, Rui Dai, Quan Kong, Lorenzo Garattoni, Gianpiero Francesca, et al.. Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection. 2023. ⟨hal-03946181⟩
35 Consultations
31 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More