Reely partners with Skillshot Media, bringing AI to esports
Reely.ai has partnered with Skillshot Media, a leader in organising and producing live esports events. Reely saw an opportunity to use its proprietary real-time stream analysis and distribution tool in the esports and gaming world.
The new partnership will give Skillshot the ability to send key moments from its esports events to social media channels in near real-time using AI-based automation. Reely will automatically include event logos and sponsorships, therefore ensuring all content is consistent and meets brand and sponsor guidelines.
"We've been interested in the gaming space for some time but our focus was primarily collegiate and professional sports," says Reely CEO Daniel Evans. "When most live sports were cancelled in the Spring of 2020, we upgraded our tech to handle the massive scale in gaming and teamed up with Skillshot to start training our models and scoring algorithms accordingly."
Skillshot has more than five years of esports experience in hosting thousands of global competitors, paying out millions in tournament prizing, and serving more than one billion esports views to date.
"We met the Reely team early last fall as they were working to extend their capabilities to esports. We definitely saw the potential even then and we're thrilled to now have these new tools for our productions. Our fans will love getting exciting moments in their hands quickly to share with friends, add their own commentary or just replay the action," said Todd Harris, founder at Skillshot Media.
How does Reely work?
Reely.ai first commercialised its Machine Vision and AI technology in the collegiate sports market in 2019. It leverages visual recognition to identify sports highlight moments in real-time, and then produce the highlight clip instantaneously.
The Reely platform supports primarily multiplayer competitive titles such as Valorant, Fortnite, Warzone, and Rocket League and top sports titles like FIFA, Madden, and NBA2K. "We were able to port most of the traditional sports models to their gaming counterparts without a lot of tuning, which just goes to show you how well EA and others have replicated the physical sport," added Evans.
Reely currently supports 17 game titles and 13 sports at a 94% accuracy rate, with plans to add new game titles each month.
Facebook Develops AI to Crackdown on Deepfakes
In light of the large tidal wave of increasingly believable deepfake images and videos that have been hitting the feeds of every major social media and news outlet in recent years, global organisations have started to consider the risk factor behind them. While the majority of deepfakes are created purely for amusement, their increasing sophistication is leading to a very simple question: What happens when a deepfake is produced not for amusement, but for malicious intent on a grander scale?
Yesterday, Facebook revealed that it was also concerned by that very question and that it had decided to take a stand against deepfakes. In partnership with Michigan State University, the social media giant presented “a research method of detecting and attributing deepfakes that relies on reverse engineering from a single AI-generated image to the generative model used to produce it.”
The promise is that Facebook’s method will facilitate deepfake detection and tracing in real-world settings, where the deepfake image itself is often the only information detectors have to work with.
Why Reverse Engineering?
Right now, researchers identify deepfakes through two primary methods: detection, which distinguishes between real and deepfake images, and image attribution, which identifies whether the image was generated using one of the AI’s training models. But generative photo techniques have advanced in scale and sophistication over the past few years, and the old strategies are no longer sufficient.
First, there are only so many images presented in AI training. If the deepfake was generated by an unknown, alternative model, even artificial intelligence won’t be able to spot it—at least, until now. Reverse engineering, common practice in machine learning (ML), can uncover unique patterns left by the generating model, regardless of whether it was included in the AI’s training set. This helps discover coordinated deepfake attacks or other instances in which multiple deepfakes come from the same source.
How It Works
Before we could use deep learning to generate images, criminals and other ill-intentioned actors had a limited amount of options. Cameras only had so many tools at their disposal, and most researchers could easily identify certain makes and models. But deep learning has ushered in an age of endless options, and as a result, it’s grown increasingly difficult to identify deepfakes.
To counteract this, Facebook ran deepfakes through a fingerprint estimation network (FEN) to estimate some of their details. Fingerprints are essentially patterns left on an image due to manufacturing imperfections, and they help identify where the image came from. By evaluating the fingerprint magnitude, repetition frequency, and symmetrical frequency, Facebook then applied those constraints to predict the model’s hyperparameters.
What are hyperparameters? If you imagine a generative model as a car, hyperparameters are similar to the engine components: certain properties that distinguish your fancy automobile from others on the market. ‘Our reverse engineering technique is somewhat like recognising [the engine] components of a car based on how it sounds’, Facebook explained, ‘even if this is a new car we’ve never heard of before’.
What Did They Find?
‘On standard benchmarks, we get state-of-the-art results’, said Facebook research lead Tal Hassner. Facebook added that the fingerprint estimation network (FEN) method can be used for not only model parsing, but detection and image attribution. While this research is the first of its kind, making it difficult to assess the results, the future looks promising.
Facebook’s AI will introduce model parsing for real-world applications, increasing our understanding of deepfake detection. As cybersecurity attacks proliferate, and generative AI falls into the hands of those who would do us harm, this method could help the ‘good guys’ stay one step ahead. As Hassner explained: ‘This is a cat-and-mouse game, and it continues to be a cat-and-mouse game’.