[go: up one dir, main page]

Biography

I am a master student working with Prof. Raquel Urtasun, Prof. Sanja Fidler and Prof. Ruslan Salakhutdinov in Machine Learning Group, Department of Computer Science at University of Toronto. During fall 2013, I spent four fruitful months in Department of Statistics, University of California, Los Angeles as a visiting graduate researcher, under supervision of Prof. Alan Yuille.

I received M.Sc. Degree on Electronic and Computer Engineering in Georgia Institute of Technology, Atlanta, U.S.A., and M.Eng. Degree on Information and Communication Engineering in Shanghai Jiao Tong University, Shanghai, China in 2014. I obtained my B.Eng. Degree (2007-2011) from Shanghai Jiao Tong University, Shanghai, China.

My primary research interests are computer vision and machine learning, with particular interest in object detection. Currently, I am freely exploring the beautiful and the ugly that deep learning might bring to us.

Publications

  • Yukun Zhu, Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba and Sanja Fidler, Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books, arXiv:1506.06724, 2015. [paper] [project page]
  • Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun and Sanja Fidler, Skip-Thought Vectors, arXiv:1506.06726, 2015. [paper] [GitHub]
  • Yukun Zhu, Raquel Urtasun, Ruslan Salakhutdinov and Sanja Fidler, segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection, In Computer Vision and Pattern Recognition (CVPR), Boston, 2015. [paper] [project page][GitHub]
  • Y. Zhu, J. Zhu, and R. Zhang, Contextual Object Detection With Spatial Context Prototypes, IEEE Transaction on multimedia, 2014.
  • Y. Zhu, J. Zhu, and R. Zhang, A spindle model for contextual object detection, IEEE International Conference on Image Processing (ICIP), 2013.
  • Y. Zhu, J. Zhu, and R. Zhang, Discovering spatial context prototypes for object detection, IEEE International Conference on Multimedia and Expo (ICME), 2013.