Guangyu Zhong

Email: guangyuzhonghikari [at] gmail [dot] com

GitHub: GYZHikari


I am a last year Ph.D. student at Dalian University of Technology. PreviouslyI was a visiting student at University of California at Merced. I received my B.S. degree from Dalian University of Technology in 2013.

My research interest includes video segmentation, video face recognition, and related vision problems. 

I am currently in the job market, please find my information on my ResumeGitHub, and LinkedIn.

10/2017 One paper on video story composition has been accepted by WACV 2018!

  1. Guangyu Zhong, Yi-Hsuan Tsai, Sifei Liu, Zhixun Su, Ming-Hsuan Yang, Learning Video-StoryComposition via Recurrent Neural Network, accepted by IEEE Winter Conference on Applications of Computer Vision (WACV), 2018
  2. Sifei LiuShalini De MelloJinwei GuGuangyu ZhongMing-Hsuan YangJan Kautz. Learning Affinity via Spatial Propagation Networks, Conference on Neural Information Processing Systems (NIPS), 2017. [PDF]
  3. Kihyuk Sohn, Sifei Liu, Guangyu Zhong, Xiang Yu, Ming-Hsuan Yang, Manmohan Chandraker. Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos, International Conference on Computer Vision (ICCV), 2017. [PDF]
  4. Guangyu Zhong*Yi-Hsuan Tsai*, Ming-Hsuan Yang. Weakly-supervised Video Scene Co-parsing, Asian Conference on Computer Vision (ACCV), 2016. 
    (* indicates equal 
    [PDF] (
  5. Guangyu Zhong, Yi-Hsuan Tsai, Yi-Ting Chen, Xue Mei, Danil Prokhorov, Michael James, Ming-Hsuan Yang. Learning to Tell Brake Lights with Convolutional Features, International Conference on Intelligent Transportation Systems, 2016. [PDF]
  6. Yi-Hsuan Tsai*Guangyu Zhong*, Ming-Hsuan Yang. Semantic Co-segmentation in Videos
    European Conference on Computer Vision (ECCV), 2016. (* indicates equal 
    [PDF] [Code
  7. Risheng Liu, Guangyu Zhong, Junjie Cao, Zhouchen Lin, Shiguang Shan, Zhongxuan Luo. Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 38(12): 2457-2471, 2016. [Code]
  8. Guangyu Zhong, Risheng Liu and Zhixun Su. Robust Visual Tracking via Discriminative Sequential Ranking, IEEE International Conference on Image Processing, 2015. [Paper]
  9. Guangyu Zhong, Risheng Liu, Junjie Cao and Zhixun Su. A Generalized Nonlocal Mean Framework with Object-Level Cues for Saliency Detection. The Visual Computer, 1-13, 2015. [Code]
  10. Guangyu Zhong, Bo Li, Junjie Cao and Zhixun Su. Object Level Saliency by Submodular Optimization. International Conference on Digital Home, 105-110, 2014.
  11. Risheng Liu, Guangyu Zhong, Junjie Cao and Zhixun Su. Diffuse Visual Attention on the Image: A Physical Perspective for Salient Region Detection. Journal of Electronic Imaging, 11(13): 4467-4476, 2014.
  12. Yuxia Song, Junjie Cao, Risheng Liu, Guangyu Zhong and Zhixun Su. Saliency Detection via Ranking with Reconstruction Error. Journal of Information and Computational Science, 11(13): 4467-4476, 2014. 
  13. Zhenzhen Zhang, Junjie Cao, Guangyu ZhongWangyi Liu and Zhixun Su. Object level image saliency by hierarchical segmentation. IEEE International Conference on Image Processing, 1772- 1774, 2013.

ICIP Travel Grants, 2015.
National Graduate Scholarship, 2015.

Programming Skills

C/C++ Python Matlab
MXNet Caffe Torch