Wenhan Luo

About

Wenhan Luo is a leading researcher in computer vision and reinforcement learning, with a focus on active object tracking and human motion prediction. His most impactful contribution is the development of an end-to-end active object tracking framework that integrates visual observation with camera control signals using reinforcement learning. This work, published in 2019 and cited 144 times, addresses the limitations of conventional methods that treat tracking and camera control as separate tasks. By unifying these processes, Luo’s approach enables real-world deployment in dynamic environments, such as robotics and autonomous systems, where adaptive camera movement is critical. His earlier 2018 paper on the same topic laid the groundwork for this innovation, while his 2024 work on hand motion prediction introduces a prompting-driven diffusion model, achieving 4 citations in its early stage. Luo’s research bridges theory and practice, demonstrating how reinforcement learning can solve complex, real-time vision tasks. His contributions have significant implications for surveillance, human-robot interaction, and augmented reality, making him a key figure in advancing intelligent tracking systems.

Research Focus

Key Achievements

Top Papers

1. 1
   End-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning

   144 citations · 2019
2. 2
   End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning

   6 citations · 2018
3. 3
   Prompting Future Driven Diffusion Model for Hand Motion Prediction

   4 citations · 2024

Key Collaborators

Contact & Links