Xianlei Long

Papers

Total Citations

H-Index

About

Xianlei Long is a leading researcher at the intersection of neuromorphic sensing and robotic intelligence, with key contributions in event-driven tactile perception, data augmentation for asynchronous sensors, and wide-area human action analysis. Their work addresses fundamental challenges in enabling robots to interact with the physical world through high-temporal-resolution, low-power tactile sensing. Long’s most cited paper, "Event-Driven Tactile Sensing With Dense Spiking Graph Neural Networks" (2025, 5 citations), introduces a novel framework that leverages spiking neural networks and graph structures to process event-based tactile data, achieving superior performance in object recognition and manipulation tasks. In "EventAugment: Learning Augmentation Policies From Asynchronous Event-Based Data" (2024, 5 citations), Long pioneers data augmentation strategies specifically designed for event-based vision, overcoming the limitations of traditional frame-based methods and improving model generalization. Their work "Efficient Uncertainty Estimation for a Hybrid Wide-Area Human Action Analysis System" (2024, 3 citations) further demonstrates expertise in balancing resolution, efficiency, and accuracy in multi-object action recognition. Long’s research is highly impactful for advancing neuromorphic robotics and real-time perception systems, with potential applications in autonomous manipulation, surveillance, and human-robot interaction. Their innovative approaches to spiking neural networks and event-based data processing are shaping the future of intelligent sensing.