Papers
3
Total Citations
26
H-Index
2
About
Jean Martinet is a rising researcher at the forefront of neuromorphic computer vision, specializing in the intersection of event-based sensing and Spiking Neural Networks (SNNs). Her work focuses on the critical challenge of making high-speed, low-power vision systems viable for embedded and robotic platforms. Martinet’s major contributions include pioneering methods for spatial downscaling of Dynamic Vision Sensor (DVS) event data, a crucial step for deploying these sensors on resource-constrained devices. Her 2022 paper, "Event Data Downscaling for Embedded Computer Vision," has garnered 13 citations for establishing foundational techniques in this area, while her 2023 comparative study on SNN-based downscaling methods (11 citations) provides a key benchmark for the field. Most recently, she has advanced the state of the art with "Neuromorphic Event-based Line Detection on SpiNNaker," demonstrating real-time, biologically-inspired line detection on neuromorphic hardware. By bridging the gap between event cameras and efficient neural computation, Martinet is laying the groundwork for a new generation of energy-efficient, high-speed vision systems for autonomous robots and edge AI applications.
Research Focus
Key Achievements
Top Papers
- 1Event Data Downscaling for Embedded Computer Vision13 citations · 2022
- 2
- 3Neuromorphic Event-based Line Detection on SpiNNaker2 citations · 2024