Ma HUIMing
从事三维图像认知与多模态学习交叉学科研究,将计算机视觉与认知心理学结合,取得了三维图像认知理论的原创性成果,建立了复杂环境仿真、视觉感知、认知学习、智能决策系统新理论和新技术,处于国际领先水平。
首次在国际上建立了图像认知心理测评智能系统,2016年获得吴文俊人工智能科技创新一等奖(排名第一),2017年获得日内瓦国际发明展览会银奖,教育部鉴定为“原始性创新,达到国际领先水平”;提出的基于GPU的高效能复杂环境仿真方法及应用,2017年获得教育部技术发明奖二等奖(排名第一);提出的复杂环境中三维目标认知方法,2015-2017年连续在国际最大的自动驾驶数据集(KITTI)评测中获得第一名,2018年在驾驶员状态预测国际数据集(Brain4Cars)上获得最好的成绩,属于国际领先水平,2020年获得中国图象图形学学会技术发明一等奖(排名第一)。
作为通讯作者在TPAMI、TIP、TITS、PR、CVPR、NIPS、ICCV、ICIP等发表论文100余篇,单篇他引超过2100次。作为负责人承担了国家重点研发计划子课题、国家自然科学基金、专项重点基金、国际国内企业合作等30余项科研项目,获批及申请专利十余项,两项专利完成了科研成果转化,实现了从基础理论、核心技术到应用的突破性进展。
教育经历:
(1) 1998-09 至 2001-07, 北京理工大学, 机电工程系机电工程专业, 博士
(2) 1995-09 至 1998-04, 北京理工大学, 机电工程系模式识别与智能系统专业, 硕士
(3) 1990-09 至 1994-06, 郑州大学, 计算机与自动化系工业电气自动化专业, 学士
科研与学术工作经历:
(1) 2019-11 至 今, kaiyun体育登录网页入口, kaiyun体育登录网页入口, 教授
(2) 2015-01 至 2019-10, 清华大学, 电子工程系, 副研究员
(3) 2006-12 至 2014-12, 清华大学, 电子工程系, 副教授
(4) 2011-03 至 2011-09, 美国匹兹堡大学, 医公司, 访问学者
(5) 2001-08 至 2006-12, 清华大学, 电子工程系, 讲师
期刊:
1. Chu, H., Mo, L., Wang, R., Hu, T., & Ma, H. Visibility of points: Mining occlusion cues for monocular 3D object detection. Neurocomputing, 2022.6
2. Sheng Yi, Huimin Ma, Xiang Wang, Tianyu Hu, Xi Li, Yu Wang. Weakly-supervised semantic segmentation with superpixel guided local and global consistency, Pattern Recognition, 2022.1
3. Huazhen Chu, Chao Le, Rongquan Wang, Xi Li, Huimin ma, Learning Representative Viewpoints in 3D Shape Recognition, The Visual Computer, 2021.7
4. Huazhen Chu, Huimin Ma, Haizhuang Liu, Rongquan Wang, Pedestrian Instance Segmentation with Prior Structure of Semantic Parts,Pattern Recognition Letter, 2021.6
5. Xi Li, Huimin Ma, Jiansheng Chen, Hongbing Ma, Single Annotated Pixel Based Weakly Supervised Semantic Segmentation under Driving Scenes, Pattern Recognition, 2021.3
6. Xiaoqian Zhang, Huimin Ma, Mouyu Wu, Tianyu Hu, LIDAR: Learning from Imperfect Demonstrations with Advantage rectification, Frontiesr of Computer Science, 2021.6
7. Sheng Yi; Huimin Ma, PHD.; Xi Li; Yu Wang, WSODPB: Weakly Supervised Object Detection with PCSNet and Box Regression Module, Neurocomputing, 2020.7
8. Yidong Wang, Lisha Mo, Huimin Ma, Jian Yuan, OccGAN: Semantic Image Augmentation for Driving Scenes, Pattern Recognition Letter, 2020.8
9. Ruiqi Lu, Huimin Ma, Yu Wang, Semantic Head Enhanced Pedestrian Detection in a Crowd,Neurocomputing, 2020.8
10. Xiang Wang · Sifei Liu · Huimin Ma* · Ming-Hsuan Yang, Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning, International Journal of Computer Vision, 2020.2
11. Dong Zhou, Huimin Ma*, Xiang Wang, Xiaoqin Zhang,Yuhan Dong, Driving Behavior Prediction Considering Cognitive Prior and Driving Context, Transactions on Intelligent Transportation Systems, 2020.2
12. Xi Li, Huimin Ma*, Weaklier Supervised Semantic Segmentation with,Only One Image Level Annotation per Category, IEEE Transactions on Image Processing, 2019.7
13. Jinghuan Wen · Huimin Ma∗ · Xiong Luo, Deep Generative Smoke Simulator: Connecting Simulated and Real Data, The Visual Computer, 2019.7
14. Yidong Wang, Lisha Mo, Xiong Luo, Huimin Ma∗, Essential Element-Region driven Model in Image Recognition, Neurocomputing, 2019.4
15. Jinghuan Wen and Huimin Ma*, Real-time Smoke Simulation Based on Vorticity Preserving Lattice Boltzmann Method. The Visual Computer, 2018.5
会议:
1. Kun Song, Yuchen Wu, Jiansheng Chen, Tianyu Hu, Huimin Ma, Gestalt-Guided Image Understanding for Few-Shot Learning, Asian Conference on Computer Vision 2022 (accepted)
2. Haizhuang Liu, Huimin Ma et.al,Eliminating Spatial Ambiguity for Weakly Supervised 3D Object Detection without Spatial Labels, ACM International Conference on Multimedia 2022 (accepted)
3. X. Zhang, H.Ma et al. Multi-Task Long-Range Urban Driving Based on Hierarchical Planning and Reinforcement Learning, IEEE International Intelligent Transportation Systems Conference 2021
4. Ziyu Xiong, Huimin Ma*, YiLin Wang, Tianyu Hu, Qingmin Liao, LiDAR-based 3D Video Object Detection with Foreground Context Modeling and Spatiotemporal Graph Reasoning, IEEE International Intelligent Transportation Systems Conference 2021
5. Shen Ruizhe, Qi Zhan, Yu Wang, and Huimin Ma, Depression Detection by Analysing Eye Movements on Emotional Images, IEEE International Intelligent Transportation Systems Conference 2021
6. Yuxin Lin, Huimin Ma, Zeyu Pan, Rongquan Wang. Depression Detection By Combining Eye Movement With Image Semantics, International Conference on Image Processing 2021
7. Haizhuang Liu, Huimin Ma, Yanxian Chen, Xi Li, Tianyu Hu. PLNL-3DSSD:part-aware 3d single stage detector using local and nonlocal attention mechanism, International Conference on Image Processing 2021
8. Yuanxin Zhang, Huimin Ma*, Yu Wang, Attention Value Decomposition for Deep Multi-agent Reinforcement Learning,International Conference on Pattern Recognition 2020
9. Yanxian Chen, Huimin Ma*, Xi Li, Xiong Luo, S-VoteNet: Deep Hough Voting with Spherical Proposal for 3D Object Detection, International Conference on Pattern Recognition 2020
10. Yahui Wang, Huimin Ma∗ Xinpeng Xing Zeyu Pan, Eulerian Motion Based 3DCNN Architecture for Facial Micro-expression Recognition, International Conference on Multimedia Modeling 2020
11. Xiang Wang, Shaodi You, Xi Li, Huimin Ma, Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features, IEEE Conference on Computer Vision and Pattern Recognition 2018
12. Zhichen Zhao,Huimin Ma, Shaodi You, Single Image Action Recognition using Semantic Body Part Actions, International Conference on Computer Vision 2017
13. Xiaozhi Chen, Huimin Ma, Ji Wan, Bo li, Tian Xia, Multi-View 3D Object Detection Network for Autonomous Driving, IEEE Conference on Computer Vision and Pattern Recognition 2017
纵向项目:
1. 不确定环境下小样本认知学习与目标识别理论和方法,国家自然科学基金委,2021
2. 精确智能技术,重大专项,2020
3. 欠数据驱动下的复杂动态目标的感知,重大专项,2019
4. 脑动态认知精神理论启发的新智能算法和模型,重大项目,2019
5. 智能复杂体系仿真,重大专项,2019
6. 基于人-车-环境协同理解的自动驾驶监测系统研发,北京市科委项目,2019
基于机器视觉的环境目标检测与识别与驾乘状态监测、评估和意图识别,国家重点研发计划项目子课题
7. 零、小样本学习——基于认知心理学的不完整目标识别,专项项目,2018
横向项目:
1. 光电信号半物理验证系统软件协作研究与开发,启元实验室,2022
2. 多要素XXX感认知协同理解与智能决策,中国XXXX广研究所,2022
3. 基于人工智能技术的新型精神健康诊疗及干预方法研究,青岛认知人工智能研究院,2022
4. 建设基于Apollp平台的目标检测算法实验研究基地,北京百度网讯科技有限公司,2020
5. 三维目标再识别应用技术,同方威视科技股份有限公司,2019
6. 无源干扰仿真研究,中国船舶集团公司第七一〇研究所,2018
2020年获得中国图象图形学学会技术发明一等奖
2018年在驾驶员状态预测国际数据集(Brain4Cars)上获得最好的成绩
2017年获得教育部技术发明奖二等奖
2016年获得吴文俊人工智能科技创新一等奖
2015年至今连续多次在国际最大的自动驾驶数据集(KITTI)评测中获得第一名
2010年,荣获北京市三八红旗奖章
获批专利14项
基于图像认知的心理状态评测方法及系统,教育部鉴定为“原始性创新,达到国际领先水平”
基于GPU的高效能复杂环境仿真方法,教育部鉴定为“总体技术达到国际先进水平”