Can I read Unsupervised Deep Representations for Learning Audience Facial Behaviors on EtoBox?

Unsupervised Deep Representations for Learning Audience Facial Behaviors by Saha, Suman; Navarathna, Rajitha; Helminger, Leonhard; Weber, Romann is a scholarly article available to read on EtoBox.

What is Unsupervised Deep Representations for Learning Audience Facial Behaviors about?

In this paper, we present an unsupervised learning approach for analyzing facial behavior based on a deep generative model combined with a convolutional neural network (CNN). We jointly train a variational auto-encoder (VAE) and a generative adversarial network (GAN) to learn a powerful latent representation from footage of audiences viewing feature-length movies. We show that the learned latent representation successfully encodes meaningful signatures of behaviors related to audience engagement (smiling & laughing) and disengagement (yawning). Our results provide a proof of concept for a more general methodology for annotating hard-to-label multimedia data featuring sparse examples of signals of interest.

Author

Saha, Suman; Navarathna, Rajitha; Helminger, Leonhard; Weber, Romann

Published

2018

Language

EN