Papers
5
Total Citations
26
H-Index
4
About
Yuchuan Gong is a leading researcher in energy-efficient domain-specific AI hardware, with a focus on deep-learning-based visual object detection and tracking (VODT) for mobile and embedded systems such as autonomous vehicles, drones, smart robots, and VR/AR devices. His most impactful contribution is the development of the DL-VOPU, an energy-efficient domain-specific visual object processing unit that supports multi-scale semantic feature extraction, achieving 22.7 TOPS/W and garnering 9 citations. Gong has pioneered reconfigurable AI processors that enable online object learning, as demonstrated in his RAODAT architecture, which balances high energy efficiency with flexible detection and tracking tasks. His work on lightweight pedestrian detection engines, featuring a two-stage low-complexity detection network and adaptive region focusing, addresses the computational bottlenecks of deep learning in real-time applications. With over 26 citations across his top papers, Gong’s innovations are critical for advancing intelligent edge computing, making high-performance visual AI feasible in power-constrained environments. His research stands out for its practical impact on smart robotics and surveillance, earning recognition for pushing the boundaries of domain-specific accelerator design.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5