A Priori Data and A Posteriori Decision Fusions for Human Action Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

A Priori Data and A Posteriori Decision Fusions for Human Action Recognition

Julien Cumin
  • Fonction : Auteur correspondant
  • PersonId : 977626

Connectez-vous pour contacter l'auteur
Grégoire Lefebvre

Résumé

In this paper, we tackle the challenge of human action recognition using multiple data sources by mixing a pri-ori data fusion and a posteriori decision fusion. Our strategy applied from 3 main classifiers (Dynamic Time Warping, Multi-Layer Perceptron and Siamese Neural Network) using several decision fusion methods (Voting , Stacking, Dempster-Shafer Theory and Possibility Theory) on two databases (MHAD (Ofli et al., 2013) and ChAirGest (Ruffieux et al., 2013)) outperforms state-of-the-art results with respectively 99.85% ± 0.53 and 96.40% ± 3.37 of best average correct classification when evaluating a leave-one-subject-out protocol.
Fichier principal
Vignette du fichier
VISAPP2016-FUSION.pdf (1011.06 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01282008 , version 1 (03-03-2016)

Identifiants

  • HAL Id : hal-01282008 , version 1

Citer

Julien Cumin, Grégoire Lefebvre. A Priori Data and A Posteriori Decision Fusions for Human Action Recognition. 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Mar 2016, Roma, Italy. ⟨hal-01282008⟩
95 Consultations
260 Téléchargements

Partager

Gmail Facebook X LinkedIn More