13741

EmoNets: Multimodal deep learning approaches for emotion recognition in video

Samira Ebrahimi Kahou, Xavier Bouthillier, Pascal Lamblin, Caglar Gulcehre, Vincent Michalski, Kishore Konda, Sebastien Jean, Pierre Froumenty, Aaron Courville, Pascal Vincent, Roland Memisevic, Christopher Pal, Yoshua Bengio
Ecole Polytechique de Montreal, Universite de Montreal, Montreal, Canada
arXiv:1503.01800 [cs.LG], (5 Mar 2015)

@article{kahou2015emonets,

   title={EmoNets: Multimodal deep learning approaches for emotion recognition in video},

   author={Kahou, Samira Ebrahimi and Bouthillier, Xavier and Lamblin, Pascal and Gulcehre, Caglar and Michalski, Vincent and Konda, Kishore and Jean, Sebastien and Froumenty, Pierre and Courville, Aaron and Vincent, Pascal and Memisevic, Roland and Pal, Christopher and Bengio, Yoshua},

   year={2015},

   month={mar},

   archivePrefix={"arXiv"},

   primaryClass={cs.LG}

}

Download Download (PDF)   View View   Source Source   

955

views

The task of the emotion recognition in the wild (EmotiW) Challenge is to assign one of seven emotions to short video clips extracted from Hollywood style movies. The videos depict acted-out emotions under realistic conditions with a large degree of variation in attributes such as pose and illumination, making it worthwhile to explore approaches which consider combinations of features from multiple modalities for label assignment. In this paper we present our approach to learning several specialist models using deep learning techniques, each focusing on one modality. Among these are a convolutional neural network, focusing on capturing visual information in detected faces, a deep belief net focusing on the representation of the audio stream, a K-Means based "bag-of-mouths" model, which extracts visual features around the mouth region and a relational autoencoder, which addresses spatio-temporal aspects of videos. We explore multiple methods for the combination of cues from these modalities into one common classifier. This achieves a considerably greater accuracy than predictions from our strongest single-modality classifier. Our method was the winning submission in the 2013 EmotiW challenge and achieved a test set accuracy of 47.67% on the 2014 dataset.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: