Meta AI Video Similarity Challenge: Descriptor Track (Open Arena)

Help keep social media safe by identifying whether a video contains a manipulated clip from one or more videos in a reference set. #society

advanced practice
Completed dec 2023
38 joined

Meta AI

Meta AI focuses on bringing the world together by advancing AI, powering meaningful and safe experiences, and conducting open research - both fundamental and applied. They publish their discoveries in peer-reviewed academic journals and conferences, and build AI technologies used by billions of people around the world.

Video Similarity Challenge & Dataset

Misinformation is the biggest obstacle to truth online. While the majority of online users manipulate videos in benign ways, there have been a great deal of instances where videos with the intent to misinform and spread hate have resulted in online and offline harm.

There are multiple cross-industry efforts to combat the threat of misinformation and abuse on social media. Data provenance is one area of focus since it is a high-prevalence issue that’s applicable across multiple domains such as copyright infringement, integrity problems, and scams.

Meta AI is engaging in this space by compiling a dataset to help build detection systems that better understand video similarity, and running a challenge to provide global benchmarks for identifying manipulated videos to combat various abuses online that involve video manipulation.

Getting scalable visual similarity detection right can reduce the amount of exposure to harmful content that online communities, businesses, and content moderators face from bad actors. The Video Similarity Dataset is an essential tool in the fight against malicious video manipulation.

You can learn more here: