Yulia Sandamirskaya

Achieving nearly full semantic accuracy with just 4.7% of the computational resources challenges the norms of dense segmentation in AI vision systems.

Event-based cameras can dramatically enhance hand detection accuracy, even in low-light and high-motion scenarios, thanks to a novel synthetic dataset.

Neuromorphic hardware can now continually learn new actions from event camera data with 100x energy reduction and 16x lower latency compared to edge GPUs.