Viorica Patraucean - Massively Parallel Video Nets Power Robotic Sight
Keynote: Massively Parallel Video Nets Power Robotic Sight
Robotics, autonomous vehicles and many other domains need to process exponential amounts of video with strict power and latency bottlenecks. This is critical for this types of use cases which need to make decisions in real-time on limited hardware. Viorica will enlighten us with her recent work on massively parallel video nets and how it’s especially relevant for real world low-latency/low-power applications. Previously she worked on 3D shapes processing in the Machine Intelligence group of the Engineering Department in Cambridge, after completing a PhD in image processing at ENSEEIHT–INP Toulouse. Irrespective of the modality - image, 3D shape, or video - her goal has always been the same: design a system that comes closer to human perception capabilities.
- Viorica Patraucean, Google DeepMind, Research Scientist
LDV Vision Summit 2018