· Zhidong DENG
· Professor
· Department of Computer Science and Technology
· Joined Department: 1992
· Email:michael@tsinghua.edu.cn
· URL:http://cs.tsinghua.edu.cn/dzd.html
· Phone:+86-10-62796830
Education background
Bachelor of Computer Science & Automation, Sichuan University, Chengdu, China, 1986;
Ph.D. in Computer Science & Automation, Harbin Institute of Technology, Harbin, China, 1991.
Social service
Chinese Association of Automation (CAA): Fellow (2018), Member of Board of Directors (2008-2013; 2013-2018; 2018-).
Chinese Association of Automation (CAA): Chair, Technical Committee on Intelligent Automation (2013-2018;2018-); Vice Chair, Technical Committee on Intelligent Manufacturing System (2017-2022).
China Computer Federation (CCF): Distinguished Member (2020).
National High-tech R&D Program of China (863 Program): Assistant Panel Leader, Intelligent Robot Subject Expert Panel (1997-2001).
China Artificial Intelligence Industry Innovation Alliance: Chair, Expert Committee (2017-).
SSE (Shanghai Stock Exchange) STAR Market: Member, the 1st Advisory Committee, (2019-).
Areas of Research Interests/ Research Projects
Artificial Intelligence (including Visual Deep Neural Network and Deep Reinforcement Learning), Computational Neuroscience, Self-driving Car, and Advanced Robotics.
My past research areas cover Virtual Reality (1998-2001), Wireless Sensor Network (2001-2009), and Computational Biology (2002-2010).
National Natural Science Foundation of China: Novel Visual Transformer Method for Autonomous Navigation in Big Data and Few-shot Scenarios (2022-2025);
National Key R&D Program of China: Research on Environmental Perception, Self-learning, and Intelligent Interaction of Service Robots in Dynamic Nursing Scenarios (2017-2021);
National Natural Science Foundation of China: Key Technologies and Prototype Development for Self-driving Car under Comprehensive Urban Environment (2015-2017);
National Natural Science Foundation of China: Key Technologies on Artificial Cognition and Unmanned Autonomous Vehicle Integration Platform (2009-2012);
National Natural Science Foundation of China: Large-Scale Functional Column Cortex Assembly-Like Recurrent Neural Network Model: Theory, Methodology, and Application (2008-2010);
National 863 High-Tech Program: A Comprehensive Design Strategy of Modularized Universal Robot Architecture (2007-2009);
National 863 High-Tech Program: Multi-Robot Systems for Coal-Mine Underground Disaster Inspection and Rescue (2006-2008);
Joint Project with NSF USA: Best-First Search for Sequence Alignment (2002-2003);
Joint Project with DARPA USA: CATScan: Constraint-based Techniques for NEST (2001-2002).
Research Status
The current research areas of my team cover: 1) artificial intelligence and computational neuroscience (including self-supervised learning, visual Transformer with knowledge reasoning, visual-text semantic object detection, scene and object graph understanding, deep unsupervised learning, deep fuzzy neural network, and deep reinforcement learning, 2) self-driving car (including AI-based environmental perception and autonomous navigation, intelligent decision-making and path planning with self-learning capabilities), and 3) mobile robotics (such as AI-based indoor scene segmentation and graphic parsing, generic object detection, and behavior prediction, cognitive maps and SLAM navigation, natural interaction, and information fusion based on deep learning). In summary, we have been attempting to develop next generation artificial intelligence that has understandability, common sense, and knowledge reasoning capability.
I received the B.S. degree from Sichuan University, Chengdu, China, in 1986 and the Ph.D. degree from Harbin Institute of Technology (HIT), Harbin, China, in 1991, respectively. From 1992 to 1994, as a postdoctoral researcher at Tsinghua University, my research interests got involved in fuzzy neural network models, fast BP learning algorithms, and asynchronous learning control. In the end of 1994, I became an Associate Professor at Tsinghua University. From 1996 to 1997, I served as a Research Associate at Hong Kong Polytechnic University, Kowloon, Hong Kong, China. During that period, I mainly worked on reinforcement learning approaches. From 2001 to 2003, I was a Visiting Professor with Washington University in St. Louis, St. Louis, MO, USA, where I took part in DARPA- and NSF-funded projects related to networked embedded system technologies (NEST) and novel ncRNA gene prediction, respectively. Since 2000, I have been a Full Professor with Tsinghua University. So far I have authored or co-authored more than 290 papers and 5 books, including international peer-reviewed academic journals like IEEE TNN,TNNLS,and TITS and top-class international conferences such as CVPR, ICCV, ECCV, AAAI, IJCAI, ICPR, ICIP, ECAI, ITSC, IV, ICRA, and IROS.
Honors & Awards
Ministry of Education of China: The Teaching and Research Award for Outstanding Young Teachers in Higher Education Institutions (2001);
Ministry of Education of China: Fok Ying-Tong Education Foundation for Young Teachers in the Higher Education Institutions of China (1999);
Ministry of Education of China: Third Place Award of Science and Technology Progress (Fundamental Category) (1998);
Tsinghua University: 1st THU Outstanding Postdoctoral Researcher Award (1997);
Ministry of Education of China: Second Place Award of Science and Technology Progress (1997);
Ministry of Aeronautics & Astronautics of China: Third Place Award of Science and Technology Progress (1992);
National Natural Science Foundation of China: Creative Research Groups (as a Member) (2007-2009; 2004-2006);
World Robot Conference (WRC-2016): Outstanding Team Award of Self-driving Car Competition (2016);
China Intelligent Vehicle Future Challenge (IVFC): The Best Organizational Contribution Award (2017).
Academic Achievement
[1] Jiajun Fei, Ziyu Zhu, Wenlei Liu, Zhidong Deng, Mingyang Li, Huanjun Deng, and Shuo Zhang, DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction, In Proc. 36th AAAI Conference on Artificial Intelligence (AAAI-2022, oral), Vancouver, BC, Canada, February 22 - March 1, 2022.
[2] Hongchao Lu, Longwei Fang, Matthieu Lin, and Zhidong Deng, Feature Enhanced Projection Network for Zero-shot Semantic Segmentation, In Proc. the 2021 IEEE International Conference on Robotics and Automation (ICRA-2021), Xi'an, China, May 30-June 5, 2021.
[3] Zhongsheng Hou, Shida Liu, Taotao Tian, Zhidong Deng, Lei Guo, Path Tracking Control of a Self-Driving Wheel Excavator via an Enhanced Data-Driven Model-Free Adaptive Control Approach, IET Control Theory & Applications, vol.14, no.2, pp.220-232, JAN 29 2020.
[4] Xiaolong Liu, Zhidong Deng, Yuhan Yang, Recent Progress in Semantic Image Segmentation, Artificial Intelligence Review, vol. 52, no. 2, pp. 1089-1106, June 2019. DOI 10.1007/s10462-018-9641-3 (ESI Highly Cited Papers)
[5] Shiyao Wang, Hongchao Lu, and Zhidong Deng, Fast Object Detection in Compressed Video, In Proc. International Conference on Computer Vision (ICCV-2019), Seoul, Korea, pp. 7103-7112, October 27-November 2, 2019.
[6] Shida Liu, Zhongsheng Hou, Taotao Tian, Zhidong Deng, and Zhenxuan Li. A Novel Dual Successive Projection-based Model-Free Adaptive Control Method and Application to an Autonomous Car, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019. DOI:10.1109/TNNLS.2019.2892327
[7] Guorun Yang, Xiao Song, Chaoqing Huang, Zhidong Deng, Jianping Shi, and Bolei Zhou. DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios, IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2019), Long Beach, CA, USA, June 16 - June 21, 2019.
[8] Zhidong Deng, Lipu Zhou. Detection and Recognition of Traffic Planar Objects Using Colorized Laser Scan and Perspective Distortion Rectification, IEEE Transactions on Intelligent Transportation Systems (TITS ), vol.19, no.5, pp. 1485-1495, May 2018.
[9] Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, and Jiaya Jia. SegStereo: Exploiting Semantic Information for Disparity Estimation, In Proc. 15th European Conference on Computer Vision (ECCV-2018), Munich, Germany, pp. 660-676, September 8-14, 2018.
[10] Shiyao Wang, Yucong Zhou, Junjie Yan, and Zhidong Deng. Fully Motion-Aware Network for Video Object Detection, In Proc. 15th European Conference on Computer Vision (ECCV-2018), Munich, Germany, pp. 542-557, September 8-14, 2018.
[11] Shiyao Wang, Minlie Huang, and Zhidong Deng. Densely Connected CNN with Multi-scale Feature Attention for Text Classification, In Proc. the 27th International Joint Conference on Artificial Intelligence (IJCAI-2018), Stockholm, Sweden, pp. 4468-4474, July 13-19, 2018.
[12] Xiaolong Liu, Zhidong Deng, Hongchao Lu, Lele Cao. Benchmark for Road Marking Detection: Dataset Specification and Performance Baseline, In Proc. IEEE 20th International Conference on Intelligent Transportation Systems (ITSC-2017), Yokohama, Japan, October 16-19, 2017.
[13] Zhidong Deng, Zhenyang Wang, and Shiyao Wang. Stochastic Area Pooling for Generic Convolutional Neural Network, In Proc. 22nd European Conference on Artificial Intelligence (ECAI-2016), The Hague, Netherlands, pp. 1760 -1761, Aug. 29 - Sept. 02, 2016.
[14] Zhenyang Wang, Zhidong Deng, and Shiyao Wang. Accelerating convolutional neural networks with dominant convolutional kernel and knowledge pre-regression, In Proc. 14th European Conference on Computer Vision (ECCV-2016), Amsterdam, The Netherlands, pp. 533-548, October 11-14, 2016.
[15] Zhenbo Cheng, Zhidong Deng, Xiaolin Hu, Bo Zhang, and Tianming Yang. Efficient reinforcement learning of a reservoir network model of parametric working memory achieved with a cluster population winner-take-all readout mechanism, Journal of Neurophysiology, vol.114, no.6, pp.3296–3305, October, 2015.
[16] Lipu Zhou, Zhidong Deng. LIDAR and Vision-Based Real-Time Traffic Sign Detection and Recognition Algorithm for Intelligent Vehicle, In Proc. the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC-2014), Hyatt Regency Qingdao, Qingdao, China, October 8-11, 2014, pp.578-583.
[17] Lipu Zhou, Zhidong Deng. Perspective Distortion Rectification for the Planar Object Based on LIDAR and Camera Data Fusion, In Proc. the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC- 2014), Hyatt Regency Qingdao, Qingdao, China, October 8-11, 2014, pp.270-275.
[18] Lipu Zhou, Zhidong Deng. Extrinsic Calibration of a Camera and a Lidar Based on Decoupling the Rotation from the Translation, In Proc. the 2012 IEEE Intelligent Vehicles Symposium (IV-2012), Alcal de Henares, Spain, pp.642-648, June 3-7, 2012.
[19] Wentao Yao, Zhidong Deng, and Zhenhua Chen. A Global and Local Condensation for Lane Tracking, In Proc. the 15th International IEEE Annual Conference on Intelligent Transportation Systems (ITSC-2012), Anchorage, Alaska, USA, pp. 276-281, Sep. 16-19, 2012.
[20] Dandan Song, Yang Yang, Bin Yu, Binglian Zheng, Zhidong Deng, Bao-Liang Lu, Xuemei Chen, and Tao Jiang. Computational prediction of novel non-coding RNAs in Arabidopsis thaliana, BMC Bioinformatics, vol.10, suppl.1, pp. (S36) 1-12, 2009.
[21] Zhidong Deng and Yi Zhang. Collective behavior of a small-world recurrent neural system with scale-free distribution, IEEE Transactions on Neural Networks (TNN), vol.18, no.5, pp.1364-1375, 2007.
[22] Zhidong Deng,Jianjun Niu, and Jingdan Zhang. A realistic 3D reverse modeling system based on real-world sampling dataset, In Proc. the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2006), Beijing, China, pp. 5327-5332, Oct. 9-15, 2006.
[23] Z. D. Deng and W. X. Zhang. Localization and dynamic tracking using wireless-networked sensors and multi-agent technology: First Steps, IEICE Trans. on Fundamentals of Electronics, Communications and Computer Sciences, vol.E85-A, no.11, pp.2386-2395, 2002.
[24] Zengqi Sun, Zhidong Deng, and Zaixing Zhang. Intelligent Control Theory and Technology (2nd Edition). Tsinghua University Press, Beijing, September 2011 (1st Edition, 1997). (In Chinese)
[25] Bo Zhang, Tianmiao Wang, Zhidong Deng, et. al. (Eds.). Report on Robot Development Strategy Study: The Chinese Historical Review, Technologies, Industry, Standards, and Government Policy. Weapon Industry Press, Beijing, 2009. (In Chinese)