Close
Meta Platforms Inc.'s artificial intelligence research team has introduced Segment Anything 2, an enhanced version of the machine learning model designed to identify objects and things within images, now extended to videos. The announcement was made by Meta Chief Executive Mark Zuckerberg during a fireside chat with Nvidia Corp. CEO Jensen Huang at SIGGRAPH 2024. SA2, a segmentation model, can describe and identify objects in images and videos, even when partially obscured or complex.
The development of SA2 represents a significant advancement in computer vision technology, enabling the application of image segmentation to videos, a feat previously deemed impossible due to processing limitations. The model, trained on a vast dataset including 50,000 annotated videos, is open-sourced and available for download on GitHub. Zuckerberg highlighted the commercial interests behind the project, emphasizing the goal of enhancing Meta's offerings through AI innovation.
The Business Journals 14month
Isomorphic Labs, the AI drug discovery platform that was spun out of Google's DeepMind in 2021, has raised external capital for the first time. The $600
How to level up your teaching with AI. Discover how to use clones and GPTs in your classroom—personalized AI teaching is the future.
Trump's Third Term? AI already knows how this can be done. A study shows how OpenAI, Grok, DeepSeek & Google outline ways to dismantle U.S. democracy.
Sam Altman today revealed that OpenAI will release an open weight artificial intelligence model in the coming months. "We are excited to release a powerful new open-weight language model with reasoning in the coming months," Altman wrote on X.
Log in
Sign Up
AI Tools - Popular
AI Tools - Categories
GPTs - Categories
AI for Jobs
