Papers
6
Total Citations
61
H-Index
5
About
Jiaolong Yang is a versatile researcher whose work spans computer vision, robotics, and artificial intelligence, with particular expertise in 3D reconstruction, autonomous navigation, and robotic manipulation. His most-cited contribution, "Deep Single-View 3D Object Reconstruction with Visual Hull Embedding" (2019, 23 citations), advances the field of 3D perception by leveraging deep convolutional neural networks to overcome the challenges posed by high-dimensional object spaces. Complementing this, his 2017 work on thin-structure obstacle detection (17 citations) addresses a critical yet underexplored safety challenge for autonomous platforms such as self-driving cars and drones, demonstrating his commitment to real-world robotic applications. Earlier foundational work on monocular robot self-localization (2010) and RGB-D camera calibration (2013) reflects a strong grounding in sensor fusion and spatial reasoning. More recently, Yang has pushed toward the frontier of embodied AI, contributing to large Vision-Language-Action models through CogACT (2024) and scalable dexterous grasping with UniGraspTransformer (2025). Taken together, his trajectory reveals a researcher steadily bridging classical robotics and modern deep learning, making meaningful contributions at each stage of this technological evolution.
Research Focus
Key Achievements
Top Papers
- 1Deep Single-View 3D Object Reconstruction with Visual Hull Embedding23 citations · 2019
- 2
- 3Monocular vision based robot self-localization8 citations · 2010
- 4
- 5
- 6