Computer vision continues to evolve at remarkable speed, with breakthroughs in detection, tracking, and spatial understanding powering everything from industrial automation to robotics and AR. This session brings together researchers and engineers at the forefront of vision innovation to explore the latest techniques—object tracking, segmentation, scene reconstruction, and multimodal vision models—and how they’re being deployed in real-world systems. Panelists will discuss advances in foundation models for vision, improvements in data efficiency, and the fusion of visual understanding with language and motion. Expect a deep dive into both the algorithms and infrastructure that are redefining how AI perceives and interprets the world, and gain practical insight into how these tools are being applied in autonomous systems, manufacturing, logistics, and interactive media.
