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.
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). He’s worked on many projects across sectors including retail, marketing, civil engineering, and private equity. The highlights of his career include his work being showcased at the Copenhagen Democracy Summit, presenting at O’Reilly conferences, BBC events, and being featured on BBC Newswround. Alex holds a PhD in theoretical physics from Imperial College London.
For exhibition and sponsorship opportunities, email strataconf@oreilly.com
For information on trade opportunities with O'Reilly conferences, email partners@oreilly.com
View a complete list of Strata Data Conference contacts
©2019, O’Reilly UK Ltd • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • confreg@oreilly.com