北京大学 English
北京大学 English
科学研究
科学研究
首页 > 科学研究 > 研究方向

研究方向

主动视觉计算与学习

 

可视信息是人类、智能机器进行日常生活和交流的关键，为后者提供理解和分析。因此，视觉计算和学习被运用在许多新兴技术领域，包括无人系统、增强现实、机器人操作和数字创作等。当前主动式视觉感知和学习正在成为研究趋势，智能体通过渐近式地与外界交互不断提升自身的感知和认知能力。

 

 

代表性科研成果

 

  • Xiangyu Kong, Bo Xin, Yizhou Wang, Gang Hua, “Collaborative Deep Reinforcement Learning for Joint Object Search,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, July 21-26, 2017.
  •  Tianyang Zhao, Yifei Xu, Mathew Monfort, Wongun Choi, Chris Maker, Yibiao Zhao, Yizhou Wang, Yingnian Wu, "Multi-Agent Tensor Fusion for Contextual Trajectory Prediction," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, June 16-20, 2019.
  • Yingming Zuo, Weichao Qiu, Lingxi Xie, Fangwei Zhong, Yizhou Wang, Alan Yuille, "CRAVES: Controlling Robotic Arm With a Vision-Based Economic System," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, June 16-20, 2019.
  • Wenhan Luo, Peng Sun, Fangwei Zhong, Tong Zhang, Yizhou Wang, "End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 22, No. 6, pp. 1634-1646, June 2020.
  • Siyan Dong, Kai Xu, Qiang Zhou, Andrea Tagliasacchi, Shiqing Xin, Matthias Nießner, Baoquan Chen, "Multi-Robot Collaborative Dense Scene Reconstruction," ACM Transactions on Graphics (TOG), Vol. 38, No. 4, pp. 84: 1-16, July 2019.

 

计算经济学

 

作为计算机和经济学的交叉方向，我们的兴趣在于社会经济科学，大规模市场设计，纳什均衡计算，多智能体信息系统，区块链经济等具体方向。在以上方向的研究中，我们将重点放在广义方法论和系统的开发中。我们用到的工具将包括博弈论，密码学，信息论，机器学习，统计，随机算法，理论经济学等。

 

 

代表性科研成果

 

  • Yuqing Kong, "Dominantly Truthful Multi-task Peer Prediction with a Constant Number of Tasks," ACM-SIAM Symposium on Discrete Algorithms (SODA), Salt Lake City, USA, January 5-8, 2020.
  • Xiaotie Deng, Tao Lin and Tao Xiao, "Private Data Manipulation in Optimal Sponsored Search Auction," the Web Conference (WWW), Taipei, April 20-24, 2020.

 

智能交互计算

 

智能交互计算通过研发新的计算理论方法与技术，赋能人、智能体（机器、智能软件系统）、与环境，提升人、智能体和环境间的协同合作功效。通过建立不同学科之间的桥梁，发展复合型学科，既服务于医疗健康、智能制造、经济金融、网络安全等国家重大需求，也惠及人们的日常生活与工作，如智慧城市、社交娱乐与人文艺术等。

 

 

代表性科研成果

 

  • Fangwei Zhong, Peng Sun, Wenhan Luo, Tingyun Yan, Yizhou Wang, "AD-VAT+: An Asymmetric Dueling Mechanism for Learning and Understanding Visual Active Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
  • Jing Li, Jing Xu, Fangwei Zhong, Xiangyu Kong, Yu Qiao and Yizhou Wang, "Pose-Assisted Multi-Camera Collaboration for Active Object Tracking," the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New York, USA, February 7-12, 2020.
  • Yunhai Wang, Mingliang Xue, Yanyan Wang, Xinyuan Yan, Baoquan Chen, Chi-Wing Fu, Christophe Hurter, "Interactive Structure-aware Blending of Diverse Edge Bundling Visualizations," IEEE Transactions on Visualization and Computer Graphics (TVCG), Vol. 26, No. 1, pp. 687-696, January 2020.

 

量子计算

 

量子计算是计算机科学、信息科学与量子物理相结合而产生的新兴交叉学科，为人类提供后摩尔时代的信息处理技术，为二十一世纪信息科学的发展提供新的原理和方法，是未来物理学和信息学发展的重大方向之一。量子计算利用量子物理不同于经典物理的特性为计算机科学、信息科学提供了新的应用，超越经典算法的量子算法、量子传感和量子精密测量等。同时，量子计算理论使用了信息论的数学、理论计算机的语言与工具解决量子物理中的问题。这种多学科领域的交叉对各个学科领域提供了全新的理解角度，进而反哺量子物理、计算理论等基础研究。

 

      

 

代表性科研成果