Junyu Gao    高君宇   Ph.D. Student National Lab of Pattern Recognition Institute of Automation, Chinese Academy of Sciences 95, Zhongguancun East Road, Beijing 100190, P.R.China Email: gaojunyu2012@gmail.com   gaojunyu2015@ia.ac.cn

Biography

I am currently a four-year bachelor-straight-to-PhD student in Mutimedia Computing Group ( MMC ), National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, advised by Prof. Changsheng Xu and Associate Prof. Tianzhu Zhang. I received a BE degree from the Computer Science Department of Xi’an Jiaotong University ( XJTU ), in 2015.

My research interests include Multimedia Computing, Deep Learning and Computer Vision. My recent work is mainly about deep learning based video understanding, with a focus on visual tracking and video classification.

Publications

Journal Articles

• 
  SMART: Joint Sampling and Regression for Visual Tracking,
  Junyu Gao, Tianzhu Zhang, Changsheng Xu.
  IEEE Transactions on Image Processing ( TIP ), 2019
  [ Paper ]
• 
  P2T: Part-to-Target Tracking via Deep Regression Learning,
  Junyu Gao, Tianzhu Zhang, Xiaoshan Yang, Changsheng Xu.
  IEEE Transactions on Image Processing ( TIP ), 2018
  [ Paper ] [ Code ]
• 
  Deep Relative Tracking,
  Junyu Gao, Tianzhu Zhang, Xiaoshan Yang, Changsheng Xu.
  IEEE Transactions on Image Processing ( TIP ), 2017
  [ Paper ] [ Code for Deep Relative Model ]
• 
  Robust Visual Tracking Method via Deep Learning,
  Junyu Gao, Tianzhu Zhang, Xiaoshan Yang, Changsheng Xu.
  Chinese Journal of Computers , 2015
  

  [ Paper ]

Conference Proceedings

• 
  Graph Convolutional Tracking,
  Junyu Gao, Tianzhu Zhang, Changsheng Xu.
  IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ), 2019
  

  [ Paper ] [ Project ]

• 
  I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs,
  Junyu Gao, Tianzhu Zhang, Changsheng Xu.
  Association for the Advancement of Artificial Intelligence ( AAAI ), 2019
  

  [ Paper ] [ Code ]

• 
  Watch, Think and Attend: End-to-End Video Classification via Dynamic Knowledge Evolution Modeling,
  Junyu Gao, Tianzhu Zhang, Changsheng Xu.
  ACM Multimedia ( MM ), 2018
  

  [ Paper ]

• 
  A Unified Personalized Video Recommendation via Dynamic Recurrent Neural Networks,
  Junyu Gao, Tianzhu Zhang, Changsheng Xu.
  ACM Multimedia ( MM ), 2017
  

  [ Paper ]

Honors & Awards

• Baidu Fellowship, 2018
• National Scholarship, 2018
• CAS-BHPB Scholarship, 2018
• Pacemaker to Merit Student, University of Chinese Academy of Sciences, 2018
• Rokid-CASIA Scholarship, 2017
• Rank: 1 / 51, Unsupervised setting, Visual Object Tracking Challenge 2017 (VOT2017), the second author
• Excellent Student, University of Chinese Academy of Sciences, 2017
• Rank: 6 / 70, Visual Object Tracking Challenge 2016 (VOT2016), the first author
• Excellent Student, University of Chinese Academy of Sciences, 2016
• National Scholarship, 2014
• National Inspirational Scholarship, 2013
• National Inspirational Scholarship, 2012