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

5
H-Index
6
Papers
61
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Deep Single-View 3D Object Reconstruction with Visual Hull Embedding
23 citations · 2019
📈 Most Prolific Year: 2019 (1 Papers)
🤝 Key Collaborators: 37
🏛 Institutions: Microsoft Research Asia (China), Microsoft Research (United Kingdom), Beijing Institute of Technology

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 15 days ago