Weilin Wan

About

Weilin Wan is a researcher at the forefront of computer vision and robotics, with a primary focus on human perception and tracking. Her most cited work, "Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks" (2019, 3 citations), addresses a critical challenge in robotics: reliably tracking the human body in cluttered, real-world environments. Wan’s key contribution lies in bridging the gap between geometric tracking and machine learning-based pose estimation. By introducing a fully convolutional neural network for part segmentation, she developed a method that maintains high accuracy even under severe occlusions—a common failure point for existing techniques. This work has significant implications for human-robot interaction, enabling robots to work safely and effectively alongside people. While her citation count is still growing, Wan’s research is notable for its practical impact on deformable tracking, a cornerstone for applications in autonomous systems, augmented reality, and assistive robotics. Her approach demonstrates a deep understanding of both the theoretical and applied challenges in visual perception, marking her as an emerging voice in the field.

Research Focus

Key Achievements

Top Papers

1. 1
   Part Segmentation for Highly Accurate Deformable Tracking in Occlusions via Fully Convolutional Neural Networks

   3 citations · 2019

Key Collaborators

Contact & Links