| 李俊 青年副研究员 硕士生导师 复旦大学 智能复杂体系基础理论与关键技术实验室 青年副研究员 Email:jun_li@fudan.edu.cn |
个人简介
专注于人工智能和机器学习的基础研究，主要包括深度神经网络的优化和泛化理论研究，以及深度神经网络在图像、视频和生物脑网络领域的应用。入选复旦新工科人才等多项人才计划。至今累计在国际人工智能/深度学习的顶级会议发表论文10余篇，并多次受邀进行主题报告。
研究兴趣
深度神经网络
代表成果
Ruizhe Zheng*, Jun Li*, Yi Wang, Tian Luo, Yuguo Yu, ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges, AAAI Conference on Artificial Intelligence, [2023], (Oral).
Tan Yu, Jun Li, Yunfeng Cai, Ping Li, Constructing Orthogonal Convolutions in an Explicit Manner, International Conference on Learning Representations, [2022].
Jianwen Xie, Yaxuan Zhu, Jun Li, Ping Li, A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model, International Conference on Learning Representations, [2022].
Jun Li, Sinisa Todorovic, Action Shuffle Alternating Learning for Unsupervised Action Segmentation, IEEE/CVF Conference on Computer Vision and Pattern Recognition, [2021].
Jun Li, Sinisa Todorovic, Anchor-Constrained Viterbi for Set-Supervised Action Segmentation, IEEE/CVF Conference on Computer Vision and Pattern Recognition, [2021].
Jun Li, Sinisa Todorovic, Set-Constrained Viterbi for Set-Supervised Action Segmentation, IEEE/CVF Conference on Computer Vision and Pattern Recognition, [2020].
Jun Li, Fuxin Li, Sinisa Todorovic, Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform, International Conference on Learning Representations, [2020].
Jun Li, Peng Lei, Sinisa Todorovic, Weakly Supervised Energy-Based Learning for Action Segmentation, IEEE/CVF International Conference on Computer Vision, [2019].
