Logo LVSN
EnglishAccueil
A proposPersonnesRecherchePublicationsEvenementsProfil
A propos
Publications

 

 

 

 

CERVIM

REPARTI

MIVIM

Sequential Emotion Recognition using Latent-Dynamic Conditional Neural Fields


Julien-Charles Lévesque, Louis-Philippe Morency and Christian Gagné


Abstract - A wide number of problems in face and gesture analysis involve the labeling of temporal sequences. In this paper, we introduce a discriminative model for such sequence labeling tasks. This model involves two layers of latent dynamics, each with their separate roles. The first layer, the neural network or gating layer, aims to extract non-linear relationships between input data and output labels. The second layer, the hidden-states layer, aims to model temporal sub-structure in the sequence by learning hidden-states and their transition dynamics. A new regularization term is proposed for the training of this model, encouraging diversity between hidden-states. We evaluate the performance of this model on an audiovisual dataset of emotion recognition and compare it against other popular methods for sequence labeling.

download document

Bibtex:

@inproceedings{Lévesque950,
    author    = { Julien-Charles Lévesque and Louis-Philippe Morency and Christian Gagné },
    title     = { Sequential Emotion Recognition using Latent-Dynamic Conditional Neural Fields },
    booktitle = { IEEE Conference on Automatic Face and Gesture Recognition },
    address   = { Shanghai, China },
    year      = { 2013 },
    month     = { April },
    journal   = { IEEE Conference on Automatic Face and Gesture Recognition }
}

Dernière modification: 2013/01/14 par jclev7

     
   
   

©2002-. Laboratoire de Vision et Systèmes Numériques. Tous droits réservés