吕凯

博士、讲师

基本信息

办公电话:010-51688648 电子邮件: lvkai@bjtu.edu.cn
通讯地址:北京海淀区交大科技大厦9013 邮编:100044

研究兴趣

主要研究人工智能技术在图像视觉感知和智能机器控制的应用,研究方向大类包含:计算机视觉 和 强化学习


欢迎本科同学参与大创项目、提前进组进行学习和学术训练。


团队b站学术主页:北交INSIS强化学习组个人主页-哔哩哔哩视频 (bilibili.com)

具体研究方向包括:

  • 目标重识别
  • 强化学习视觉泛化
  • 多智能体强化学习

上述研究方向,近两年以一作或通讯作者CCF A类会议和IEEE/ACM trans期刊等发表9篇学术论文。

(IJCAI 1篇,AAAI 2篇,TITS 1篇,TMM 1篇,TCSVT 1篇,TOMM 2篇,TVT 1篇)

教育背景

(1) 2016-09 至 2021-06, 北京航空航天大学, 软件工程, 博士, 导师:李未院士、熊璋教授

(2) 2019-01 至 2020-01, 澳大利亚国立大学, 计算机科学与技术, 联合培养博士, 导师:Liang Zheng 博士

(3) 2018-06 至 2019-01, 新加坡科技设计大学, 计算机科学与技术, 联合培养博士, 导师:Liang Zheng 博士

(4) 2014-09 至 2016-09, 北京航空航天大学, 计算机科学与技术, 硕士, 导师:盛浩教授

工作经历

(1) 2023年9月至今,北京交通大学计算机学院,讲师

(2) 2021年6月至2023年8月, 北京交通大学计算机学院, 师资博士后

招生专业

  • 计算机技术硕士
  • 软件工程硕士
  • 大数据技术与工程硕士
  • 计算机科学与技术硕士
  • 人工智能硕士
  • 新一代电子信息技术(含量子技术等)硕士

科研项目

  • 红果园省部级"企事业"(新): XX提取与XX技术研究, 2024-2025
  • 自然科学横向项目: 新能源场站智慧化关键技术研究与系统开发, 2024-2029
  • 红果园省部级"企事业"(新): 某模型, 2024-2024
  • 红果园省部级"企事业"(新): 某系统自主认知目标识别算法XX样本生成模块, 2024-2024
  • 自然科学类人才基金项目: 面向集群协同的多智能体强化学习算法研究, 2024-2026
  • 红果园省部级"企事业"(新): 基于决策点的超实时仿真预测及评估技术研究, 2024-2024
  • 自然科学横向项目: 2022年中国高校产学研创新基金科大讯飞高校智慧教学创新研究专项, 2024-2024
  • 自然科学横向项目: 融合LLM的交通量预测与交通决策优化技术项目, 2024-2025
  • 红果园国家级"四总部": 基于多智能体强化学习的编队协同空战决策算法研究, 2024-2025
  • 红果园省部级"企事业"(新): 某系统软件项目软件开发质量数据控制服务, 2023-2024
  • 红果园省部级"企事业"(新): 基于代码大模型的航天嵌入式软件单元测试自动生成技术研究, 2023-2024
  • 自然科学横向项目: 应用监控智能算法研究课题, 2023-2024
  • 自然科学横向项目: 基于组合优化的旅客保护智能化算法技术服务, 2023-2024
  • 自然科学横向项目: 基于大数据挖掘技术的旅客附加服务推荐研究课题, 2023-2024
  • 红果园省部级"企事业"(新): XXXX流程仿真平台升级改造及软件联调保障, 2023-2025
  • 国家自然科学基金“面上”: 复杂遮挡下基于光场图像的场景恢复技术研究, 2024-2027
  • 红果园省部级"企事业"(新): 动态数据注入的超实时仿真技术研究, 2022-2024
  • 国家自然科学基金"青年基金": 面向多视角车辆重识别的多维一致性学习方法研究, 2023-2025

教学工作

本科生课程:《操作系统》秋季-64课时

硕士研究生课程:《深度学习》暑期-32课时

博士研究生课程:《强化学习前沿理论与技术》秋季-32课时

论文/期刊

  • [TOMM 2024] Kai Lv, Haobo Chen, Chuyang Zhao, Kai Tu, Junru Chen, Yadong Li, Boxun Li, and Youfang Lin*. "Style Variable and Irrelevant Learning for Generalizable Person Re-identification." ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2024. (SCI, Q2, CCF B类期刊, IF=5.1)
  • [IJCAI 2024] Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, Kai Lv*"How to Learn Domain-Invariant Representations for Visual Reinforcement Learning: An Information-Theoretical Perspective." the 33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024. (CCF A类会议)
  • [AAAI 2024] Shuo Wang, Zhihao Wu, Xiaobo Hu, Jinwen Wang, Youfang Lin, Kai Lv*. "What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction." The 38th AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF A类会议)
  • [AAAI 2024] Hengrui Zhang, Youfang Lin, Shuo Shen, Sheng Han, Kai Lv*"Enhancing Off-policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation." The 38th AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF A类会议)
  • [TOMM 2024] Xiaobo Hu, Youfang Lin, HeHe Fan, Shuo Wang, Zhihao Wu and Kai Lv*. "Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation" ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2024. (SCI, Q2, CCF B类期刊, IF=5.1)
  • [TITS 2023] Kai Lv, Shuo Wang, Shuai Han, Youfang Lin*. "Spatially-Regularized Features for Vehicle Re-identification: An Explanation of Where Deep Models Should Focus." IEEE Transactions on Intelligent Transportation Systems (TITS), 2023. (SCI, Q1, CCF B类期刊, IF=8.5)
  • [IJCAI workshop 2023] Kai Lv, Shuai Han and Youfang Lin. "Generalization between Different Viewpoints with A Feature Selection Method for Vehicle Re-identification." 32nd International Joint Conference on Artificial Intelligence (IJCAI) Workshop 2023. 
  • [TCSVT 2023] Xiaobo Hu, Youfang Lin, Shuo Wang, Zhihao Wu and Kai Lv*"Agent-Centric Relation Graph for Object Visual Navigation." IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023. (SCI, Q1, CCF B类期刊, IF=5.859, An 2区) 
  • [TMM 2023] Shuo Wang, Zhihao Wu, Xiaobo Hu, Youfang Lin, Kai Lv*"Skill-based Hierarchical Reinforcement Learning for Target Visual Navigation." IEEE Transactions on Multimedia (TMM), 2023. (SCI, Q1, IF=8.182, An 1区)
  • Han Wang, Youfang Lin, Sheng Han and Kai Lv*"Offline Reinforcement Learning with Diffusion-Based Behavior Cloning Term." The 16th International Conference on Knowledge Science, Engineering and Management (KSEM 2023). (CCF C类会议)
  • [TVT 2022] Hengrui Zhang, Youfang Lin, Sheng Han, and Kai Lv*.  "Lexicographic Actor-Critic Deep Reinforcement Learning for Urban Autonomous Driving." IEEE Transactions on Vehicular Technology (TVT), 2022.  (SCI, Q1, IF=6.239,  An 2区)
  • Sheng Han, Youfang Lin, Zhihui Guo, and Kai Lv*"A Lightweight and Style-Robust Neural Network for Autonomous Driving in End Side Devices." Connection Science (2022). (SCI, CCF C类期刊, IF=3.53)
  • Xinze Dou, Yang Liu, Kai Lv, Zhang Xiong, and Hao Sheng. "High Confidence Attribute Recognition for Vehicle Re-Identification." 2021 IEEE International Conference on Image Processing (ICIP): IEEE, 2021. (CCF C类会议)
  • [TIP 2020] Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, and Liang Zheng. "Pose-Based View Synthesis for Vehicles: A Perspective Aware Method." IEEE Transactions on Image Processing (TIP), 2020: 5163-74. (SCI, CCF A类期刊, IF=9.34, An 1区)
  • [TMM 2020] Kai Lv, Hao Sheng, Zhang Xiong, Wei Li, and Liang Zheng. "Improving Driver Gaze Prediction with Reinforced Attention." IEEE Transactions on Multimedia (TMM), 2020: 4198-207. (SCI, CCF B类期刊, IF=6.513, An 1区)
  • [JIOT 2020] Hao Sheng, Kai Lv*, Yang Liu, Wei Ke, Weifeng Lyu, Zhang Xiong, and Wei Li. "Combining Pose Invariant and Discriminative Features for Vehicle Reidentification." IEEE Internet of Things Journal 8, no. 5 (2020): 3189-200. (SCI, IF=9.471, An 1区)
  • Hantao Hu, Yang Liu, Kai Lv, Yanwei Zheng, Wei Zhang, Wei Ke, and Hao Sheng. "Camera Style Guided Feature Generation for Person Re-Identification." International Conference on Wireless Algorithms, Systems, and Applications: Springer, Cham, 2020. (CCF C类会议)
  • Kai Lv, Heming Du, Yunzhong Hou, Weijian Deng, Hao Sheng, Jianbin Jiao, and Liang Zheng. "Vehicle Re-Identification with Location and Time Stamps." CVPR Workshops, 2019
  • Chao Li, Lei Liu, Kai Lv, Hao Sheng, and Wei Ke. "Combine Coarse and Fine Cues: Multi-Grained Fusion Network for Video-Based Person Re-Identification." International Conference on Knowledge Science, Engineering and Management: Springer, Cham, 2018. (CCF C类会议)
  • Kai Lv,  Hao Sheng, Yanwei Zheng, Zhang Xiong, Wei Li, and Wei Ke. "Task-Specific Neural Networks for Pose Estimation in Person Re-Identification Task." Pacific Rim Conference on Multimedia: Springer, 2017.
  • Hao Sheng, Kai Lv, Jiahui Chen, and Wei Li. "Robust Visual Tracking Using Correlation Response Map." 2016 IEEE International Conference on Image Processing (ICIP): IEEE, 2016. (CCF C类会议)


社会兼职

担任知名国际会议领域主席,包括:


  1. ACM Multimedia (ACM MM)
  2. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  3. Advanced Video and Signal Based Surveillance (AVSS)


担任知名国际会议和期刊的审稿人,包括:

  • Annual Conference on Neural Information Processing Systems (NeurIPS)
  • The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • IEEE Trans on MultiMedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)等。