DeepAI
Log In Sign Up

Unsupervised Deep Representations for Learning Audience Facial Behaviors

05/10/2018
by   Suman Saha, et al.
0

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.

READ FULL TEXT

page 2

page 4

11/29/2016

Deep Quantization: Encoding Convolutional Activations with Deep Generative Model

Deep convolutional neural networks (CNNs) have proven highly effective f...
01/22/2020

From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder

Conditional Generative Models are now acknowledged an essential tool in ...
12/14/2018

Learning Latent Subspaces in Variational Autoencoders

Variational autoencoders (VAEs) are widely used deep generative models c...
04/01/2021

Drug Discovery Approaches using Quantum Machine Learning

Traditional drug discovery pipeline takes several years and cost billion...
10/09/2018

Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks

While objects from different categories can be reliably decoded from fMR...
04/03/2020

Disassembling Object Representations without Labels

In this paper, we study a new representation-learning task, which we ter...
12/10/2019

Learning to generate new indoor scenes

Deep generative models have been used in recent years to learn coherent ...