职称:教授
联系电话:010-68914849
E-mail:peimt@bit.edu.cn
通信地址:威尼斯87978797
个人信息
裴明涛,威尼斯87978797教授,博士生导师。2004年获威尼斯87978797工学博士学位,2009年至2011年在美国加州大学洛杉矶分校作访问学者。中国计算机学会会员,中国计算机学会计算机视觉专委会委员,中国计算机学会普适计算专委会委员,中国图象图形学会多媒体专委会委员。目前主要科学研究方向为计算机视觉和模式识别。在国际重要学术期刊IEEE TIP,TMM,IEEE TITS,CVIU以及ICCV,AAAI,IJCAI等国际顶级会议上发表学术论文60余篇,获国家发明专利8项。
个人主页:https://peimingtao.github.io
科研方向
计算机视觉,模式识别,人工智能
代表性学术成果
期刊论文:
[1] Min Yang, Mingtao Pei,Yunde Jia, Online maximum a posteriori tracking of multiple objects using sequential trajectory prior, Image and Vision Computing 94 (2020) 58–67.
[2] Yanmei Dong,Mingtao Pei,Xiaofeng Liu,Meng Zhao, Scene-Specific Multiple Cues Integration for Multi person Tracking[J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 12(3):511-518.
[3] Changyong Yu, Chengtang Yao,Mingtao Pei, Yunde Jia,Diffusion-based kernel matrix model for face liveness detection, Image and Vision Computing 89 (2019) 88–94.
[4] 董震,裴明涛,基于异构哈希网络的跨模态人脸检索方法,计算机学报,Vol 42, No 1,2019.01
[5] Jing Chenchen, Dong Zhen, Pei Mingtao, Jia Yunde. Heterogeneous Hashing Network for Face Retrieval across Image and Video Domains. IEEE Transactions on Multimedia, 2018.
[6]Zhen Dong, Chenchen Jing, Mingtao Pei, Yunde Jia, Deep CNN based Binary Hash Video Representations for Face Retrieval, Pattern Recognition, 2018.05
[7]Zhen Dong, Mingtao Pei, Yunde Jia, Orthonormal dictionary learning and its application to face recognition, Image and Vision Computing 51 (2016) 13–21
[8] Wu, Yuwei; Pei, Mingtao; Yang, Min, Robust Discriminative Tracking via Landmark-Based Label Propagation, IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol 24,pp:1510-1523,MAY 2015
[9] Dong, Zhen; Wu, Yuwei; Pei, Mingtao, Vehicle Type Classification Using a Semisupervised Convolutional Neural Network, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, Vol16,pp:2247-2256,AUG 2015
[10] Mingtao Pei,Zhangzhang Si, Benjamin Yao, Song-Chun Zhu, Learning and parsing video events with Goal and Intent Prediction, Computer Vision and Image Understanding(CVIU), Volume 117, Issue 10, Pages 1203-1548, October 2013.
会议论文:
[1] Chuanqi Zang, Mingtao Pei,YU Kong, Few-shot Human Motion Prediction via Learning Novel Motion Dynamics, IJCAI 2020
[2] Siyu Li, Mingtao Pei, Vehicle Re-Identification by Deep Feature Fusion Based on Joint Bayesian Criterion, ICPR 2018
[3] Zhen Dong, Su Jia, Tianfu Wu, Mingtao Pei, Face Video Retrieval via Deep Learning of Binary Hash Representations, AAAI Conference on Artificial Intelligence, 2016, Phoenix, Arizona USA.
[4] Min Yang, Mingtao Pei, Jiajun Shen and Yunde Jia , Robust Online Multi-Object Tracking by Maximum a Posteriori Estimation with Sequential Trajectory Prior , ICONIP 2015
[5] Dong, Zhen; Pei, Mingtao; He, Yang, Vehicle Type Classification Using Unsupervised Convolutional Neural Network, 22nd International Conference on Pattern Recognition (ICPR), Stockholm, SWEDEN, AUG 24-28, 2014
[6] Mingtao Pei, Zhen Dong, Meng Zhao, Event Recognition by Social Roles in Continuous Video, IEEE International Conference on Multimedia and Expo (ICME), San Jose, 2013 (Oral).
[7] Yong Duan, Mingtao Pei, Yunde Jia, Probabilistic Depth Map Fusion for Real-Time Multi-View Stereo , ICPR 2012 (Oral)
[8] Yi Xie,Mingtao Pei,Zhao Liu, Tianfu Wu, Tracking Pedestrian with Multi-Component Online Deformable Part-Based Model, ACCV 2012
[9] Mingtao Pei,Yunde Jia, Songchun Zhu, Parsing Video Events with Goal inference and Intent Prediction, ICCV 2011
[10] Zhangzhang Si, Mingtao Pei, Benjamin Yao, Songchun Zhu, Unsupervised Learning of Event AND-OR Grammar and Semantics from Video. ICCV 2011
发明专利
[1] 裴明涛,贾云得,“一种侧面轮廓和人耳相结合的身份识别装置”,专利号:ZL 2006 1 0127147.2. 授权时间:2008.08.13
[2] 裴明涛,郭志强,杨敏,王永杰,董震,“一种基于可变形部件模型的车牌及驾驶员人脸定位方法”, 专利号:ZL 2012 1 0352669.8. 授权时间:2014.12.31
[3] 裴明涛,王亚菲,“一种基于像素点可区分度的自然路标及着陆区域确定方法”, 专利号:201210352611.3. 授权时间:2016.04.06
[4] 杨敏,裴明涛等,“一种智能交通监控系统中的高分辨率视频车辆检测方法”,专利号:ZL 2014 1 0035329.1. 授权时间:2017.06.16
[5] 贾云得,杨敏,裴明涛,一种采用时间动态表观模型的实时在线多目标跟踪方法,专利号:ZL 2015 1 1029753.6 授权时间:2019.04.05
[6] 裴明涛,张博,一种基于立体视觉和行为分析的头戴式预防近视装置,专利号:ZL 2017 1 0126985.6, 申请时间:2017.3.6 授权时间:2019.02.22
[7] 贾云得,沈家峻,许彬,裴明涛,一种可触摸现场实时视频图像的远程呈现交互方法和系统,专利号:ZL 2016 1 0803805.9, 授权时间:2019.06.14
[8] 裴明涛,李佩霖,梁玮,一种基于虚拟现实与手势识别的远程呈现交互方法与系统,专利号:ZL 2016 1 1025123.6 授权时间:2020.04.14
承担科研情况
[1] 国家自然科学基金:视频中事件的内容分析语义与描述, 2015.01---2018.12, 项目负责人
[2] 国家自然科学基金:视频中交互行为的自动分析与理解, 2013.01---2015.12, 项目负责人
[3] 国家973项目子课题: 基于下降图像序列的行星表面地形分析及路标跟踪技术,2014.01---2016.12, 项目负责人
[4] 国家973项目子课题:行星表面自然路标检测与着陆器位姿估计方法研究, 2012.01---2013.12, 项目负责人
[5] 教育部留学归国人员启动基金:基于环境上下文信息的视频行为分析与理解方法研究, 2013.01---2014.12, 项目负责人
[6] 威尼斯87978797基础研究基金:基于机器学习的视频事件分析与理解, 2011.01---2012.12, 项目负责人
所获奖励
威尼斯87978797优秀科技成果奖一等奖一项,排名第二 中国兵器工业集团公司科学技术奖二等奖一项,排名第二 教育部技术发明奖二等奖一项排名第六
社会兼职
中国计算机学会会员,中国计算机学会计算机视觉专委会委员,中国计算机学会普适计算专委会委员,中国图象图形学会多媒体专委会委员。