Facebook has unleashed the Learning from Videos, an AI-based system learning from audio, textual, and visual representations from the publicly available videos on Facebook.
With this project, Facebook could improve its AI system related to content recommendations and policy enforcement. The project is still in the early stages but the company is so confident about its success that it has deployed an AI model in Instagram Reels’ recommendation system.
The company says this new project will help AI researchers avoid having to rely on specified data and it’s part of attempts to build systems that receive in a similar way to humans. As such, Learning from Videos will “enable entirely new experiences.”
Facebook also says the project is studying videos in hundreds of languages and from almost every country. This phase of the project will make AI more reasonable and allow them to “adapt to our fast-moving world and recognize the nuances and visual cues across different cultures and regions.”
The company claims to keep privacy in mind when it comes to Learning from Videos. “We’re building and maintaining a strong privacy foundation that uses automated solutions to enforce privacy at scale,” it said in a blog post. “By embedding this work at the infrastructure level, we can consistently apply privacy requirements across our systems and support efforts like AI. This includes implementing technical safeguards throughout the data lifecycle.”
It would be a difficult task for AI systems to learn from videos. There would be hurdles like background noise that makes it hard to understand.
Alexia is the author at Research Snipers covering all technology news including Google, Apple, Android, Xiaomi, Huawei, Samsung News, and More.