Presented By
O’Reilly + Cloudera
Make Data Work
29 April–2 May 2019
London, UK

Synthetic video generation: Why seeing should not always be believing

Alexander Adam (Faculty)
14:5515:35 Wednesday, 1 May 2019
Data Science, Machine Learning & AI
Location: Capital Suite 17
Secondary topics:  Deep Learning, Media, Marketing, Advertising, Security and Privacy
Average rating: ****.
(4.00, 1 rating)

Who is this presentation for?

  • Data scientists, business leaders, and policy makers

Level

Intermediate

Prerequisite knowledge

  • Familiarity with machine learning and neural networks

What you'll learn

  • Understand the positive and negative applications of synthetic video generation
  • Gain an overview of techniques used to generate synthetic video

Description

We often find ourselves questioning the meaning of “truth” in the virtual world of imagery online. It’s well known that images can be tampered with, using tools like Photoshop. What’s less well known is that recent advances in deep learning and computer vision make it possible to manipulate videos as well. In just a few years, it will likely be possible to create synthetic video that is indistinguishable by eye from reality.

Despite the many beneficial applications of this technology (whether in special effects or dubbing), there’s no question that it’s also potentially very dangerous. For example, it will become possible to manipulate videos of public figures in the run-up to an election and make them appear to say or do things that they didn’t do.

Alex Adam offers an overview of the approaches to generating synthetic video, starting with simple face-swaps using autoencoders and moving on to discuss generative adversarial networks (GANs) and style transfer using Cycle-GAN and Recycle-GAN. Alex concludes by discussing work Faculty has been doing towards building machine learning classifiers to detect face-swapped video.

Photo of Alexander Adam

Alexander Adam

Faculty

Alex Adam is a data scientist at Faculty. He’s particularly interested in generative neural networks and their applications both in natural language processing (text generation) and computer vision (video generation). Over his career, he’s worked on many projects across sectors including retail, marketing, civil engineering, and private equity. Alex holds a PhD in theoretical physics from Imperial College London.