李俊,博士,副教授,硕士研究生导师
2020 年6月毕业于北京航空航天大学计算机学院,取得计算机科学与技术专业工学博士学位,同年9月加入yl9193永利计算机科学与技术系,主要研究兴趣包括视频行为分析、小样本学习、视觉推理、自动驾驶、对抗攻击及防御技术等。当前在计算机视觉等领域发表论文20余篇(第一作者发表ESI高被引论文一篇),其中包括国际顶级期刊(如IEEE TPAMI、TIP)、国际顶级学术会议(如AAAI、IJCAI)发表高水平学术论文8篇。CVPR、Pattern Recognition等会议和期刊的审稿人。最后,欢迎编程功底扎实、对计算机视觉工程项目、科研探索有强烈、浓厚兴趣的以及之后有读博意向的同学加入我们团队。
办公地点:北二区教学楼231室
联系方式:junmuzi@cnu.edu.cn
科研项目
[1] 国家自然基金青年项目:“面向视频行为分析的三维卷积时序建模与优化方法研究”,起止日期:2022.01—2024.12,主持;
[2] 国家重点实验室开放课题:“基于三维卷积网络的视频行为分析技术研究”,起止日期:2021.01—2022.12,主持;
[3] 北京市科委:“北京市科技新星计划”,起止日期:2019.11—2022.10,参与;
[4] 国家重点研发:“XXXX检测关键技术研究及应用”,起止日期:2019.02—2022.02,参与;
主讲课程
1.本科生课程:《人工智能原理》《人工智能数学基础》
2.研究生课程:《计算机视觉》
主要论文如下:
1. Temporal Transformer Networks with Self-Supervision for Action Recognition, Y. Zhang, J. Li, N. Jiang, G. Wu, H. Zhang, Z. Shi, Z. Liu, Z. Wu and X. Liu, IEEE Internet of Things Journal, 2023, SCI一区
2. Spatio-Temporal Adaptive Network with Bidirectional Temporal Difference for Action Recognition, Z. Li, J. Li, Y. Ma, R.Wang,Z. Shi, Y. Ding, and X. Liu, IEEE Transactions on Circuits and Systems for Video Technology, 2023, CCF B类期刊
3. Bullet-Screen-Emoj Attack with Temporal Difference Noise for Video Action Recognition, Y. Zhang, J. Li, Z. Shi, N. Jiang, Q. Geng and Y. Pei, IEEE International Conference on Multimedia and Expo, 2023. CCF B类会议(已录用)
4.Two-Branch Attention Network via Efficient Semantic Coupling for One-Shot Learning J. Li; D. Wang; X. Liu; Z. Shi; M. Wang, IEEE Transactions on Image Processing, 2022, 31: 341-351, CCF A类期刊
5. Spatio-Temporal Self-Supervision enhanced Transformer Networks for Action Recognition
Y. Zhang, H. Zhang, G. Wu, J Li*, IEEE International Conference on Multimedia and Expo (ICME) 2022,CCF B类会议
6. TMN: Temporal-Guided Multiattention Network for Action Recognition, Y. Zhang, H. Zhang, G. Wu, Y. Xu, Z. Shi and J. Li, International Conference on Pattern Recognition, 2022, CCF C类会议
7. 用于视频行为识别的高效二维时序建模网络, 栗志磊,李俊*,施智平,姜那,张永康, 计算机工程与应用,2021,CCF C类期刊
8. TSSN: Temporal self-Attention and Self-Supervision Network for Efficient Action Recognition
Y. Zhang, J Li*, Z. Shi, N. Jiang, Z. Li, ICVRV 2021,EI类会议
9.Multi-Pretext Attention Network for Few-shot Learning with Self-supervision
H Li, R Tao, J Li, H Qin, Y Ding, S Wang, X Liu, IEEE International Conference on Multimedia and Expo (ICME), 2021, CCF B类会议
10. Spatio-temporal deformable 3d convnets with attention for action recognition
J Li, X Liu, M Zhang, D Wang, Pattern Recognition 98, 107037, 2020,SCI一区期刊
11. Spatio-temporal attention networks for action recognition and detection
J Li, X Liu, W Zhang, M Zhang, J Song, N Sebe, IEEE Transactions on Multimedia 22 (11), 2990-3001, 2020,SCI一区期刊
12. Graph attention based proposal 3d convnets for action detection
J Li, X Liu, Z Zong, W Zhao, M Zhang, J Song, Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 4626-4633, 2020, CCF A类会议
13. Candidate region correlation for video action detection
Y. Li, M. Zhang, L. Hua, J. Li, D. Wang, in JVCI, 2020.
14. Dynamic Spatio-Temporal Feature Learning via Graph Convolution Networks
J. Li, X. Liu, J. Xiao, H. Li, S. Wang, L. Liu, in ICDM Workshop, 2019.
15. Progressive Generative Hashing for Image Retrieval.
Y. Ma, Y. He, F. Ding, S. Hu, J. Li, X. Liu, IJCAI, 871-877, 2018, CCF A类会议
16. Semantic object segmentation in tagged videos via detection
Y. Zhang, X. Chen, J. Li, C. Wang, C. Xia, J. Li, IEEE transactions on pattern analysis and machine intelligence 40 (7), 1741-1754, 2017,SCI一区期刊