Action Recognition with Fusion of Multiple Graph Convolutional Networks - Université Toulouse 1 Capitole Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Action Recognition with Fusion of Multiple Graph Convolutional Networks

Camille Maurice
  • Fonction : Auteur
  • PersonId : 1015990

Résumé

We propose two lightweight and specialized Spatio-Temporal Graph Convolutional Networks (ST-GCNs): one for actions characterized by the motion of the human body and a novel one we especially design to recognize particular objects configurations during human actions execution. We propose a late-fusion strategy of the predictions of both graphs networks to get the most out of the two and to clear out ambiguities in the action classification. This modular approach enables us to reduce memory cost and training times. Moreover we also propose the same late fusion mechanism to further improve the performance using a Bayesian approach. We show results on 2 public datasets: CAD-120 and Watch-n-Patch. Our late-fusion mechanism yields performance gains in accuracy of respectively +21 percentage points (pp), +7 pp on Watch-n-Patch and CAD-120 compared to the individual graphs. Our approach outperforms most of the significant existing approaches.
Fichier principal
Vignette du fichier
avss_2021(4).pdf (4.33 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03562364 , version 1 (02-03-2022)

Identifiants

Citer

Camille Maurice, Frédéric Lerasle. Action Recognition with Fusion of Multiple Graph Convolutional Networks. 2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Nov 2021, Washington, DC, United States. ⟨10.1109/AVSS52988.2021.9663765⟩. ⟨hal-03562364⟩
48 Consultations
76 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More