AI models still lose track of who is who and what's happening in a movie. A new system orchestrates face recognition and staged summarization, keeping characters straight, and plots coherent across ...

Abstract: Modern railways continue to strive for remote and automated methods to improve the visual inspection procedures for their assets. In some cases, these inspections provide new information ...

Abstract: The present paper aims to follow the development of a belt conveyor equipped with a computer vision module. The process of constructing the system with the help of CAD software, as well as ...

Perplexity Computer launches with 19 specialized AI models working in parallel to build apps, dashboards, research, and more from a single prompt.

This project aims to develop a computational framework combining computer vision, computer graphics, and machine learning to accelerate and improve the design and simulation of camera lenses.

Seattle-based Vercept developed complex agentic tools, including a computer-use agent that could complete tasks inside applications like a person with a laptop would.

New Google AI products and customer innovation include Gemini Pro, Gemini 3, AI agents, agentic vision, Google Cloud and Deep Think in 2026.