Papers
5
Total Citations
26
H-Index
4
About
Luying Que is a leading researcher in energy-efficient, domain-specific AI hardware, with a core focus on deep-learning-based visual object detection and tracking (VODT) processors. Her work directly addresses the critical challenge of deploying complex neural networks on resource-constrained platforms like autonomous drones, smart robots, and VR/AR systems. Que’s major contribution is the development of a series of reconfigurable, energy-efficient processors, most notably the **DL-VOPU** (22.7 DL-VOPU), which introduces a domain-specific architecture supporting multi-scale semantic feature extraction for mobile applications. This work, her most cited with 9 citations, exemplifies her approach of tailoring hardware to specific visual tasks rather than using general-purpose AI accelerators. She pioneered techniques such as **online object learning** and **adaptive region focusing**, enabling processors to learn and track new objects in real-time without retraining. Her 2022 reconfigurable AI processor, cited 6 times, further advanced this by achieving high energy efficiency while maintaining flexibility. With over 26 total citations across her key publications, Que’s research is pivotal for enabling next-generation intelligent systems that require real-time, low-power visual intelligence at the edge.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5