Li Zhang张力Research Assistant Professor
The Hong Kong Polytechnic University, Hong Kong SAR, China |
|
Biography
I am currently a research assistant professor at The Hong Kong Polytechnic University (PolyU) .
Prior to this, I obtained my doctoral degree from University of Science and Technology of China (USTC) .
My research interests focus on computer vision and embodied AI, especially Vision-tactile Perception and Manipulation.
I actively collaborate with leading industry partners such as Tencent AI Lab, IFLYTEK, Astribot,
focusing on cutting-edge research in pose perception.
I am a strong advocate of sharing🌱, collaborating🤝, advancing🚀, and innovating💡.
Passionate about bridging fundamental research with real-world impact, I strive to ensure my work contributes to both academic progress and practical value.
If you’re interested in collaborating or would like to connect, feel free to reach out via email (邮箱：zanly20.zhang@polyu.edu.hk) or Wechat (微信号：zanly20)! 😊
News
Researches
My current research focuses on the visual perception of articulated and flexible objects,
aiming to develop advanced 3D pose estimation methods to empower robots with fine manipulation and dexterous grasping capabilities.
While significant progress has been made in enabling robotic operation in idealized settings,
challenges related to robustness and adaptability persist in complex and unstructured environments such as underwater exploration, medical intervention, and industrial inspection.
In response to the unique perception demands posed by these scenarios, I am actively expanding my research into new directions,
with an emphasis on critical visual perception problems and corresponding solutions for underwater and medical robotics.
CVPR 2025 L Zhang, M Xu, J Wang, Q Yu, L Yang, Y Li, C Lu, R Wang, L Liu
[Paper]
[BibTeX]
[Project/Codes]
[TL;DR:] 2D Virtual try-on methods can be introduced into the garment pose perception. AAAI 2025 L Zhang, H Jiang, Y Huo, Y Zhong, J Wang, X Wang, R Wang, L Liu
[Paper]
[BibTeX]
[Project/Codes]
[TL;DR:] 6D pose estimation without depth information. BMVC 2024 W Xu, L Zhang, Q Li, Q Wu, L Wu, L Liu
[Paper]
[BibTeX]
[Project/Codes]
[TL;DR:] An novel Integrated Framework for four mainstream articulation tasks. ACM MM 2024 L Zhang, Z Han, Y Zhong, Q Yu, X Wu, X Wang, R Wang
[Paper]
[BibTeX]
[Project/Codes]
[TL;DR:] What serves as the bridge between pose estimation and pose tracking? Answer: inter-frame priors! NeurIPS 2024(spotlight) L Zhang, Y Zhong, J Wang, Z Min, R Wang, L Liu
[Paper]
[BibTeX]
[Project/Codes]
[TL;DR:] Does 3D Convolution really need inner production? We made an exploration on ℓp-norm convolution.
Journal Reviewer Conference ServiceSelected Publications [Google Scholar]
Work/Intern Experiences
Services