"Truth is ever to be found in simplicity, and not in the multiplicity and confusion of things." -- Isaac Newton
I am now an Assistant Professor at the School of Automation, South China University of Technology ( from Mar. 2026 ). I work closely with Prof. Yang Cong on the joint supervision of graduate students. My research interests cover video understanding, human motion perception and policy learning.
After completing my Ph.D., I worked successively at Tencent AI Lab ( which has completed its historic mission ), Autel Robotics, and ByteDance, over a period of six years. During this time, I experienced the complete cycle from research conceptualization to academic publication, and from technological prototyping to final product deployment. I consider myself fortunate to have been able to revisit my field from an industrial perspective, which significantly broadened my academic horizons and deepened my understanding of technology transfer.
Prior to my journey in the industry, I received my Ph.D. degree in school of Electrical and Electronic Engineering ( EEE ) from Nanyang Technological University ( NTU ), Singapore in 2020. During this period, I was fortuanately advised by Prof. Junsong Yuan and Prof. Xudong Jiang focusing on human behavior analysis.
Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
Jiaxu Zhang, Junwu Weng, Di Kang, Fang Zhao, Shaoli Huang, Xuefei Zhe, Linchao Bao,Ying Shan, Jue Wang, Zhigang Tu
Proc. IEEE Conf. on Computer Vision and Pattern Recognition ( CVPR ), 2023
Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos
Zixiao Wang, Junwu Weng, Chun Yuan, Jue Wang
Proc. of the AAAI Conference on Artificial Intelligence ( AAAI ), 2023 [ Oral ]
Temporal Distinct Representation Learning for Action Recognition
Junwu Weng, Donghao Luo, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Xudong Jiang, Junsong Yuan
European Conference on Computer Vision ( ECCV ), 2020
Early Action Recognition with Category Exclusion using Policy-based Reinforcement Learning
Junwu Weng, Xudong Jiang, Weilong Zheng, Junsong Yuan
IEEE Transactions on Circuits and Systems for Video Technology ( T-CSVT ), 2020
Hand Point Net: 3D Hand Pose Estimation using Point Sets
Liuhao Ge, Yujun Cai, Junwu Weng, Junsong Yuan
Proc. IEEE Conf. on Computer Vision and Pattern Recognition ( CVPR ), 2018 [ Spotlight ]