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

4
H-Index
5
Papers
26
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
22.7 DL-VOPU: An Energy-Efficient Domain-Specific Deep-Learning-Based Visual Object Processing Unit Supporting Multi-Scale Semantic Feature Extraction for Mobile Object Detection/Tracking Applications
9 citations · 2023
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 26
🏛 Institutions: University of Electronic Science and Technology of China

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago