Yiming Li
Papers
1
Total Citations
4
H-Index
1
About
Yiming Li is an emerging researcher working at the intersection of computer vision, egocentric perception, and human-robot interaction. His work focuses on enabling machines to understand and anticipate human intent from first-person visual perspectives — a critical capability for building safer and more responsive robotic systems. His most recognized contribution, "EgoPAT3Dv2: Predicting 3D Action Target from 2D Egocentric Vision for Human-Robot Interaction" (2024), advances the field by tackling a particularly challenging problem: inferring precise 3D spatial targets of hand movements using only 2D egocentric video input. Rather than relying on conventional semantic action classification or coarse 2D region estimates, Li's approach pushes toward geometrically grounded prediction, offering robots a more actionable understanding of human motion intent. This work has already garnered 4 citations since its publication, signaling growing interest from the robotics and computer vision communities. Li's research sits at a timely frontier, as egocentric sensing and wearable devices become increasingly prevalent, making his contributions highly relevant for advancing intuitive, anticipatory human-robot collaboration in real-world environments.
Research Focus
Key Achievements
Top Papers
- 1