Accession Number:

AD1033850

Title:

How Deep Neural Networks Can Improve Emotion Recognition on Video Data

Descriptive Note:

Technical Report

Corporate Author:

MIT Lincoln Laboratory Lexington United States

Report Date:

2016-09-25

Pagination or Media Count:

5.0

Abstract:

There have been many impressive results obtained using deep learning for emotion recognition tasks in the last few years. In this work, we present a system that performs emotion recognition on video data using both convolutional neural networks CNNs and recurrent neural networksRNNs. We present our findings on videos from the AudioVisualEmotion Challenge AVEC2015. In our experiments, we analyze the effects of several hyperparameters on overall performance while also achieving superior performance to the baseline and other competing methods.

Subject Categories:

  • Computer Programming and Software
  • Psychology

Distribution Statement:

APPROVED FOR PUBLIC RELEASE