Jinlong Yang
Papers
1
Total Citations
190
H-Index
1
About
Jinlong Yang is a researcher whose work sits at the intersection of computer vision, 3D human body modeling, and human-robot interaction. His most recognized contribution, "Grasping Field: Learning Implicit Representations for Human Grasps" (2020), has garnered 190 citations and represents a significant advance in the realistic synthesis of human hand-object interactions — a notoriously difficult problem given the hand's exceptional degrees of freedom compared to robotic manipulators. By leveraging implicit neural representations, Yang's approach opened new avenues for generating plausible, physically consistent human grasps, a capability with far-reaching applications in animation, virtual reality, and robotic learning from human demonstration. His research addresses fundamental challenges in understanding and recreating how humans interact with their environment at a fine-grained, physically grounded level. The strong citation impact of his work reflects its relevance across multiple communities, including graphics, robotics, and machine learning. Yang's contributions have helped bridge the gap between computational models of the human body and real-world applicability, making him a notable voice in the emerging field of neural implicit representations for human motion and interaction synthesis.
Research Focus
Key Achievements
Top Papers
- 1Grasping Field: Learning Implicit Representations for Human Grasps190 citations · 2020