曾文军

讲席教授

加拿大工程院外籍院士

IEEE Fellow

副校长

wzeng-vp@eitech.edu.cn

景介绍

1990年毕业于清华大学电子工程系,1993年和1997年分别获美国圣母大学和普林斯顿大学电子工程硕士和博士学位,加拿大工程院外籍院士,曾任微软亚洲研究院高级领导团队(SLT)成员、首席研究员,现任宁波东方理工大学(暂名)副校长、讲席教授。研究方向包括人工智能、计算机视觉、多媒体分析、以及多媒体通信和安全等,累计发表79篇国际期刊论文和174篇国际会议论文,其中Web of Science核心文集引用文献228篇,获3次国际最佳论文奖,论文被引用17000多次(据Google Scholar),H-index为61。近5年在计算机视觉和人工智能顶刊(TPAMI、IJCV、SPM、TIP、TMM、TCSVT)和顶会(CVPR、ICCV、ECCV、MM、NeurIPS、ICLR、AAAI、IJCAI)发表70多项研究成果。2012级IEEE Fellow,先后担任10个IEEE顶级期刊和杂志的副总编或联合编辑、12个IEEE顶级国际会议(如ICME 2018、ICIP 2017等)的大会共同主席或技术程序委员会主席,并获得10项国际荣誉和奖项(IEEE Fellow、Leaderships、Best Papers)。


点击这里下载完整简历.pdf


研究领域

人工智能、计算机视觉、社交网络/媒体分析、多媒体通信与网络、内容/网络安全


教育背景

1993-1997:博士,美国普林斯顿大学电子工程系

1991-1993:硕士,美国圣母大学电子工程系

1985-1990:学士,清华大学电子工程系


工作经历

2021-至今:宁波东方理工大学(暂名) 讲席教授、副校长

2017-2021:微软亚洲研究院 高级领导团队(SLT)成员

2015-2021:微软亚洲研究院 西安交通大学-微软亚研院智能信息处理联合实验室主任

2014-2021:微软亚洲研究院 首席研究员

2011-2014:密苏里大学哥伦比亚分校 计算机科学系正教授

2007-2011:密苏里大学哥伦比亚分校 计算机科学系网络安全研究中心主任

2003-2014:密苏里大学哥伦比亚分校 计算机科学系移动网络与多媒体通信实验室主任

2003-2011:密苏里大学哥伦比亚分校 计算机科学系副教授(2007年9月获得终身教职)

2000-2003:PacketVideo公司(世界第一家无线视频领域的独角兽初创公司) 高级研究员(首席技术官团队)

1997-2000:卡马斯夏普实验室 研究员


学术经历(兼职)

2017-至今:中国科学技术大学 客座教授(博士生导师)

2013-至今:天津大学 客座教授

2015-2021:西安交通大学 客座教授(博士生导师)

2013-2013:华为媒体实验室 访问教授

2011-2014:北京清流迅公司(StreamOcean) 首席科学家

2011-2011:微软亚洲研究院 访问教授

2008-2011:华为技术有限公司(代表华为参与开放移动联盟) 学术顾问

2007-2008:Calidus公司(现为北京清流迅公司(StreamOcean)) 学术顾问

2006-2006:微软亚洲研究院 访问教授

1996-1996:朗讯科技公司贝尔实验室-多媒体通信实验室 实习研究员

1995-1995:松下科技公司松下信息技术实验室 实习研究员


学术兼职(部分)

编委会(部分)

2018-至今:副主编(Associate Editor),Inter. Journal of Computer Vision 2014-2017:副总编(Associate EiC),IEEE Multimedia Magazine 2009-2012:指导委员会(Steering Committee)委员,IEEE Trans. on Multimedia 2014-2016:指导委员会(Steering Committee)委员,IEEE Trans. On Mobile Comput. 2010-2015:副主编(Associate Editor),IEEE Trans. on Cir. & Sys. For Video Tech. 2009-2012:副主编(Associate Editor),IEEE Trans. on Info. Forensics & Sec. 2006-2014:副主编(Associate Editor),IEEE Multimedia Magazine 2004-2008:副主编(Associate Editor)IEEE Trans. on Multimedia 2017:客座编辑(Guest Editor),IEEE TCSVT Special Issue 2017:客座编辑(Guest Editor),Special Issue on Video Computing in the Cloud: Mobile Computing, IEEE Trans. Circuit and Systems for Video Technology 2014:客座编辑(Guest Editor),IEEE Multimedia Magazine, Fast Track Program for ICME2014 papers 2013:客座编辑(Guest Editor),ACM Trans. on Multimedia Computing Comm. and App. 2008:客座编辑(Guest Editor),Special Issue on Recent Advances in Distributed Multimedia Communications, the Proceedings of the IEEE 2004:客座编辑(Guest Editor),TMM


技术委员会(部分)

2018-2021:IEEE Jack S. Kilby信号处理奖章委员会委员 2019-至今:技术委员会委员,IEEE Sig. Proc. Society's Image,Video & Multidimensional Sig. Proc. TC. 2011-2013:技术委员会委员,Info. Forensics and Sec. TC. 2005-2009:技术委员会委员,Multimedia Sig. Proc. TC. 2007-至今:技术委员会委员,Cir. & Sys. Society's Multimedia System & Application TC. 2008-2010:IEEE通信学会多媒体通信技术委员会副主席 2018:大会主席(General co-Chair), IEEE Inter. Conference on Multimedia and Expo. 2017:技术程序委员会主席(TPC co-Chair),IEEE Inter. Conf. Image Proc. 2015:技术程序委员会主席,IEEE ChinaSIP 2013:技术程序委员会主席,IEEE Workshop on Info. Forensics and Security 2007:技术程序委员会主席,IEEE Consumer Comm. And Networking Conf. 2005:技术程序委员会主席,Multimedia Communications and Networking Symposium,IEEE Inter. Conf. Communication 2010-2011:指导委员会主席,IEEE Inter. Conf. Multimedia & Expo


获奖情况及荣誉

2020:列入斯坦福大学发布的全球 Top 2% 顶尖科学家终身科学影响力2020排行榜单 2018:行业杰出领袖奖,APSIPA(亚太信号与信息处理协会) 2016:最佳论文奖,IEEE(国际电气和电子工程师协会)视觉通信和图像处理会议 2016:最佳期刊论文奖,IEEE ComSocMMTC(通信协会多媒体通信技术委员会) 2012:最佳论文奖,2012ACM(国际计算机协会)多媒体计算和服务国际会议 2012:IEEE Fellow(国际电气和电子工程师协会会士),2012级(鉴于对多媒体通信和安全的突出贡献) 2010:杰出服务奖,IEEE ComSocMMTC(通信协会多媒体通信技术委员会)


代表性论著

书籍及书籍部分章节

l S. Deb Roy and W. Zeng, Social Multimedia Signals: A Signal Processing Approach to Social Network Phenomena, ISBN: 978-3-319-09116-7, Springer, Aug. 2014.

l S. Deb Roy, T. Mei, and W. Zeng, “Bridging social media content across web domains,” book chapter in Human-Centered Social Media Analytics edited by Y. Fu, 2013, Springer.

l W. Zeng, H. Yu and C. Lin (Eds), Multimedia Security Technologies for Digital Rights Management, ISBN:  0123694760, Elsevier, July 2006. (the first book designed to provide an in-depth and comprehensive coverage on the state-of-the-art multimedia security technologies for the DRM applications)

l W. Zeng, “Format compliant content protection,” book chapter in Multimedia Security Technologies for Digital Rights Management, W. Zeng, H. Yu and C. Lin (Eds), ISBN:  0123694760, Elsevier, July 2006.


论文

l Zhipeng Huang, Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Peng Chu, Quanzeng You, Jiang Wang, Zicheng Liu, Zheng-Jun Zha, “Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation”, in IEEE Conference on Computer Vision and Pattern Recognition, June 2022.

l Tao Yang, Xuanchi Ren, Yuwang Wang, Wenjun Zeng, “Towards Building A Group-based Unsupervised Representation Disentanglement Framework”, in International Conference on Learning Representations, April 2022.

l Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng, ”Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View”, in International Conference on Learning Representations, April 2022.

l Y. Zhang, C. Wang, X. Wang, W. Zeng, and W. Liu, “FairMOT: On the fairness of detection and re-identification in multiple object tracking”, in International Journal of Computer Vision, in Sept. 2021.

l Xiaotian Chen, Yuwang Wang, Xuejin Chen, Wenjun Zeng, “S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation,” in CVPR 2021 (Oral Paper).

l Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen, Li Zhang, “Style Normalization and Restitution for Generalizable Person Re-identification,” in CVPR, June 2020, Seattle, USA.

l P. Tang, C. Wang, X. Wang, W. Liu, W. Zeng, and J. Wang, “Object Detection in Videos by High Quality Object Linking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 5, pp. 1272-1278, May 2020.

l P. Zhang, C. Lan, J. Xing, W. Zeng, J. Xue, and N. Zheng, “View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 8, pp. 1963-1978, Aug. 2019.

l Z. Zhang, C. Lan, W. Zeng, and Z. Chen, “Densely Semantically Aligned Person Re-Identification,” IEEE Conference on Computer Vision and Pattern Recognition, June 2019.

l L. Wang, Z. Xiong, H. Huang, G. Shi, F. Wu, and W. Zeng, “High-Speed Hyperspectral Video Acquisition by Combining Nyquist and Compressive Sampling," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 4, pp. 857-870, April 2019.

l B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng, and Z. Wang, “Benchmarking Single Image Dehazing and Beyond,” IEEE Transactions on Image Processing, vol. 28, no. 1, pp. 492-505, Jan. 2019.

l A. He, C. Luo, X. Tian, and W. Zeng, “A Twofold Siamese Network for Real-Time Object Tracking,” in CVPR 2018.

l L. Wang, Z. Xiong, G. Shi, F. Wu, and W. Zeng, “Adaptive Nonlocal Sparse Representation for Dual-Camera Compressive Hyperspectral Imaging,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no 10, Oct. 2017.

l Z. Xiong, Y. Zhang, F. Wu, and W. Zeng, “Computational Depth Sensing: Toward High Performance Commodity Depth Cameras,” IEEE Signal Processing Magazine, vol. 34, no. 3, May 2017.

l S. Song, C. Lan, J. Xing, W. Zeng, and J. Liu, “An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data”, in 2017 AAAI Conference on Artificial Intelligence.

l W. Zhu, C. Lan, J. Xing, W. Zeng, Y. Li, L. Shen, X. Xie, "Co-occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks," 2016 AAAI Conference on Artificial Intelligence.

l S. Deb Roy, T. Mei, W. Zeng and S. Li, “Towards Cross Domain Learning for Social Video Popularity Prediction,” IEEE Transactions on Multimedia, Special Issue on Social Media as Sensors, vol. 15, no. 6, Oct. 2013. (IEEE ComSoc MMTC 2015 Best Journal Paper Award)

l W. Zeng and S. Lei, “Efficient frequency domain selective scrambling of video”, in IEEE Tran. Multimedia, March 2003.

l W. Zeng and B. Liu, “A statistical watermark detection technique without using original images for resolving rightful ownerships of digital images," in IEEE Trans. Image Processing, vol. 8, no. 11, pp. 1534-1548, Nov. 1999.  

l C. Podilchuk and W. Zeng, "Image-Adaptive watermarking using visual models," invited paper, IEEE Journal on Selected Areas in Communications, vol. 16, No. 4, Special Issue on Copyright and Privacy Protection, pp. 525-539, May 1998.