Songzhi Su
Papers
2
Total Citations
14
H-Index
2
About
Songzhi Su’s research lies at the intersection of computer vision and deep learning, with a focus on human pose analysis and robust scene understanding. In his influential 2016 work, Su pioneered a method for human lying-pose detection by learning rich features from objectness estimation—a technique that has garnered 11 citations and laid groundwork for applications in surveillance and healthcare monitoring. More recently, he advanced the field of visual place recognition with a 2023 study introducing a faster, lighter, yet stronger deep learning approach, achieving 3 citations and demonstrating his commitment to efficient, deployable AI systems. Su’s contributions are notable for bridging the gap between theoretical feature learning and practical, real-world performance—his work on objectness-driven feature extraction remains a reference point for researchers tackling pose estimation in cluttered environments. By prioritizing computational efficiency without sacrificing accuracy, Su’s research continues to inspire new directions in mobile robotics and embedded vision systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2