# Unsupervised Deep Representations for Learning Audience Facial Behaviors

arXiv: https://arxiv.org/abs/1805.04136 · HTML: https://mlsanity.com/paper/1805.04136/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2018.

## Built on by (most cited first, 1 of 1)

- [FERT: Real-Time Facial Expression Recognition with Short-Range FMCW Radar](https://mlsanity.com/paper/2411.11619/) (2024)

## Abstract (arXiv)

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.