ModDrop: adaptive multi-modal gesture recognition - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2016

ModDrop: adaptive multi-modal gesture recognition

Graham W. Taylor
  • Fonction : Auteur
  • PersonId : 968487
Florian Nebout
  • Fonction : Auteur

Résumé

We present a method for gesture detection and localisation based on multi-scale and multi-modal deep learning. Each visual modality captures spatial information at a particular spatial scale (such as motion of the upper body or a hand), and the whole system operates at three temporal scales. Key to our technique is a training strategy which exploits: i) careful initialization of individual modalities; and ii) gradual fusion involving random dropping of separate channels (dubbed "ModDrop") for learning cross-modality correlations while preserving uniqueness of each modality-specific representation. We present experiments on the ChaLearn 2014 Looking at People Challenge gesture recognition track, in which we placed first out of 17 teams. Fusing multiple modalities at several spatial and temporal scales leads to a significant increase in recognition rates, allowing the model to compensate for errors of the individual classifiers as well as noise in the separate channels. Futhermore, the proposed ModDrop training technique ensures robustness of the classifier to missing signals in one or several channels to produce meaningful predictions from any number of available modalities. In addition, we demonstrate the applicability of the proposed fusion scheme to modalities of arbitrary nature by experiments on the same dataset augmented with audio.
Fichier principal
Vignette du fichier
main.pdf (3.37 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01178733 , version 1 (21-07-2015)

Identifiants

  • HAL Id : hal-01178733 , version 1

Citer

Natalia Neverova, Christian Wolf, Graham W. Taylor, Florian Nebout. ModDrop: adaptive multi-modal gesture recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016. ⟨hal-01178733⟩
336 Consultations
316 Téléchargements

Partager

Gmail Facebook X LinkedIn More