Papers
5
Total Citations
26
H-Index
4
About
Conghan Jia is a leading researcher at the forefront of energy-efficient, domain-specific AI hardware for visual intelligence. His work centers on designing specialized processors that enable deep-learning-based visual object detection and tracking (VODT) in resource-constrained mobile platforms, including autonomous drones, smart robots, and AR/VR systems. Jia’s major contribution is the development of reconfigurable, domain-specific architectures that dramatically improve energy efficiency while supporting complex tasks like multi-scale semantic feature extraction and online object learning. His most cited work, "DL-VOPU" (9 citations), introduces a dedicated Visual Object Processing Unit that achieves high performance for mobile applications. He further advanced the field with the "RAODAT" processor series (6 and 5 citations), which pioneered reconfigurable AI designs with online learning capabilities, and a lightweight pedestrian detection engine (4 citations) that uses a two-stage low-complexity network. By exploiting domain-specific features and adaptive techniques, Jia’s processors overcome the high computational costs of general AI accelerators, setting a new standard for embedded visual intelligence. His cumulative work, with over 26 citations, is shaping the next generation of smart, autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5