Jianbin Tang
Papers
2
Total Citations
212
H-Index
2
About
Jianbin Tang is a leading researcher in robotic manipulation and computer vision, with a primary focus on real-time grasp detection for low-powered devices. His most impactful work, "GraspNet: An Efficient Convolutional Neural Network for Real-time Grasp Detection for Low-powered Devices" (2018, 167 citations), introduced a compact CNN architecture that achieves high grasp detection accuracy while minimizing memory and computational demands—a critical breakthrough for deploying robotics on embedded systems. Building on this, Tang developed the Densely Supervised Grasp Detector (DSGD) (2019, 45 citations), a framework that fuses layer-wise features to generate grasp confidence scores at global, region, and pixel levels, significantly enhancing detection granularity. His contributions address the longstanding trade-off between accuracy and efficiency in robotic grasping, enabling real-time performance on resource-constrained platforms. Tang's work has been widely cited in robotics and AI communities, influencing subsequent research in efficient deep learning for manipulation tasks. His achievements underscore a commitment to making intelligent grasping accessible for practical, low-power applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2Densely Supervised Grasp Detector (DSGD)45 citations · 2019