Outstanding graduates are invited to apply for full PhD Studentships within the Research Institute. For further details, please click Here

Sheng-hua Zhong

College of Computer Science and Software Engineering
Shen Zhen University
Shen Zhen, GD 518060

Emails:

Education:

 Ph.D

 M. Eng

 B. Eng

 

Department of Computing, The Hong Kong Polytechinic University

Institution of Information Engineering, Shen Zhen University

Institution of Optical Information Science and Technology, Nanjing University of Posts and Telecommunications

2013

2008

2005

 

Research interests:

Brain science, cognitive science, visual cortex modeling, deep learning, attention, memory and learning, computational modeling, artificial intelligence, machine learning, multimedia content analysis

Awards:

 Best Paper Award

 Qualcomm Award

 Women Researcher Award

ACM Intl Conference on Internet Multimedia Computing and Service

ACM Intl Conference on Multimedia

ACM Intl Conference on Internet Multimedia Computing and Service

2011

2011

2010

Professional experience:

 Postdoctoral Fellowship

 Research Associate

 Visiting Scholar

Johns Hopkins University

The Hong Kong Polytechnic University

Johns Hopkins University

08/2013 – 08/2014

04/2013 – 08/2013

06/2012 – 12/2012

Invited talks:

Research methodology in brain science.
Department of Computer Science
Shen Zhen Graduate School, Harbin Institute of Technology
Shen Zhen, China.

Computational modeling for vision science.
School of Computer Science and Engineering, South China University of Technology
Guang Zhou, China.

Video saliency detection via spatio-temporal attention modelling analysis.
Department of Computer Science
Shen Zhen Graduate School, Harbin Institute of Technology
Shen Zhen, China.

Multimedia content analysis via computational human visual model.
Department of Psychological & Brain Sciences, Johns Hopkins University
Baltimore, Maryland, USA.

Multimedia content analysis via computational human visual cognition.
Department of Computer Science
Shen Zhen Graduate School, Harbin Institute of Technology
Shen Zhen, China.

Bilinear deep learning for image classification.
Department of Computer Science, City University of Hong Kong
Hong Kong, China.

05/2015

 

04/2014

 

05/2013

 

06/2012

 

11/2011

 

08/2011

 

Research Grants (Project Leader):

Visual attention research based on contextual cueing using deep learning framework, The National Natural Science Foundation of China, No. 61502311, 240,000 RMB, 2016-2018.

Large scale computational visual attention based on deep learning, The National Science Foundation of Guangdong Province, No. 2016A030310053, 100,000 RMB, 2016-2019.

Visual attention modeling based on contextual cueing, The Science and Technology Innovation Commission of Shenzhen, No. JCYJ20150324141711640, 100,000 RMB, 2015-2017.

NSFC-Guangdong Joint Fund for supercomputing application (Stage II), the National Supercomputing Center in GuangZhou (No. NSFC2015_275)

Professional services:

- Journal Reviewer:

IEEE Transactions on Image Processing
IEEE Transactions on Neural Networks and Learning Systems
Multimedia Tools and Applications
Expert Systems with Applications
Journal of the International Measurement Confederation
Neurocomputing

<< Go Back

Publications


    Journals
  • Sheng-hua Zhong, Yan Liu*, Kien A. Hua. Field effect deep networks for image recognition with incomplete data, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 12(4), 2016.
  • Jiaxin Wu,Sheng-hua Zhong*, Jianmin Jiang, Yunyun Yang. A novel clustering method for static video summarization. Multimedia Tools and Applications. 2016. DOI:
  • Sheng-hua Zhong,Yan Liu*, To-Yee Ng, Yang Liu. Perception-oriented video saliency detection via spatio-temporal attention analysis.Neurocomputing . 2016. DOI:
  • Sheng-hua Zhong, Yan Liu*, Bin Li, Jing Long. Query-oriented unsupervised multi-document summarization via deep learning. Expert Systems with Applications. 42(21), 2015.
  • Sheng-hua Zhong,Yan Liu*, Qingcai Chen. Visual orientation inhomogeneity based scale-invariant feature transform. Expert Systems with Applications. 42(13), 2015.
  • Sheng-hua Zhong, Zheng Ma, Colin Wilson, Yan Liu, Jonathan I. Flombaum*. Why do people appear not to extrapolate trajectories during multiple object tracking? A computational investigation, 14(12). Journal of Vision (JOV). 2014.
  • Sheng-hua Zhong, Yan Liu, Yang Liu*, Changsheng Li. Water reflection recognition based on motion blur invariant moments in Curvelet space. IEEE Transactions on Image Processing (TIP). 22(11). 2013.
  • Sheng-hua Zhong,Yan Liu*, Yang Liu*, Fu-lai Chung. Region level annotation by fuzzy based contextual cueing label propagation. Multimedia Tools and Applications (MTA). 70(2). 2014.
  • Yang Liu, Yan Liu*, Sheng-hua Zhong, and Keith C.C. Chan. Tensor distance based multilinear globality preserving embedding: a unified tensor based dimensionality reduction framework for image and video classification, Expert Systems with Applications (ESWA). 39(12), 2012.
  • Heeyeon Im,Sheng-hua Zhong, Justin Halberda*. Grouping by proximity and the visual impression of approximate number in random dot arrays, Vision Research.2015.
  • Yu Zhao, Yan Liu*, Yang Liu, Sheng-hua Zhong,Kien A. Hua. Face recognition from a single registered image for conference socializing. Expert Systems with Applications (ESWA). 42(3), 2014.


  • Conferences
  • Su Mei, Shenghua Zhong*, Jianmin Jiang, Transfer learning based on A+ for image super-resolution, accept in 9th International Conference on Knowledge Science, Engineering and Management (KSEM), 2016, pp. 1-12.
  • Sheng-hua Zhong, Jiaxin Wu, Yingying Zhu*, Peiqi Liu, Jiangmin Jiang, Yan Liu, Visual orientation inhomogeneity based on convolutional neural networks, accept in 28th International Conference on Tools with Artificial Intelligence (ICTAI), 2016, pp. 1-8
  • Yingying Zhu, Chuanhua Jiang, Xiaoyan Huang, Zhijiao Xiao,Sheng-hua Zhong*. A temporal-compress and shorter SIFT research on web videos. In Proceedings of the International Conference on Knowledge Science, Engineering and Management, 2015.
  • Song-tao Wu, Yan Liu*,Sheng-hua Zhong,Yang Liu. What makes the stego image undetectable? In Proceedings of 7th ACM International Conference on Internet Multimedia Computing and Service (ICIMCS'15), 2015.
  • Sheng-hua Zhong,Qun-bo Zhang, Zheng-ping Li, Yan Liu*. Motivations and challenges in MOOCs with eastern insights. In Proceedings of International Conference on Education and Management Technology (ICEMT’15), 2015.
  • Jonathan I. Flombaum*,Sheng-hua Zhong, Bruno Jedynak, Huaibin Jiang. The microgenesis of information acquisition in visual ‘popout’. In Proceedings of the 14th annual meeting of Vision Sciences Society (VSS'15), 2015.
  • Zheng Ma,Sheng-hua Zhong, Colin Wilson, Jonathan I. Flombaum*. Kalman filter models of multiple-object tracking within an attentional window. In Proceedings of the 14th annual meeting of Vision Sciences Society (VSS'15), 2015.
  • Zhen Yang, Sheng-hua Zhong,Aaron Carass, Sarah Ying, Jerry L. Prince*. Deep learning for cerebellar ataxia classification and clinical score regression. Accept In The Medical Image Computing and Computer Assisted Intervention (MICCAI'14).
  • Sheng-hua Zhong, Zheng Ma, Colin Wilson, Jonathan I. Flombaum*. Kalman filter models of multiple-object tracking within an attentional window. In Proceeding of the 14th annual meeting of Vision Sciences Society (VSS'14), 2014.
  • Hee Yeon Im, Sheng-hua Zhong, Bruno Jedynak, Lisa Feigenson, Jonathan I. Flombaum*. Information pursuit as a model for efficient visual search. In Proceeding of the 14th annual meeting of Vision Sciences Society (VSS'14), 2014.
  • Sheng-hua Zhong,Yan Liu*. Video saliency detection via dynamic consistent spatio-temporal attention modelling. In Proceedings of 27th AAAI International Conference on Artificial Intelligence (AAAI’13), 2013.
  • Jonathan I. Flombaum*, Sheng-hua Zhong,Zheng Ma, Colin Wilson, Yan Liu. What is the marginal advantage of extrapolation during multiple object tracking? Insights from a Kalman filter model. In Proceeding of the 13th annual meeting of Vision Sciences Society (VSS'13), 2013.
  • Hee Yeon Im, Sheng-hua Zhong, Justin Halberda*. Biases in human number estimation are well-described by clustering algorithms from computer vision. In Proceeding of the 13th annual meeting of Vision Sciences Society (VSS'13), 2013.
  • Sheng-hua Zhong,Yan Liu*, Gangshan Wu. S-SIFT: A Shorter SIFT without least discriminative visual orientation. In Proceeding of the 2012 IEEE/WIC/ACM International Conference on Web Intelligence (WI’12), 2012.
  • Sheng-hua Zhong,Yan Liu*, Yao Zhang, Fu-lai Chung. Attention modeling for face recognition via deep learning. In Proceeding of the 34th annual meeting of the Cognitive Science Society (CogSci’12), 2012.
  • Yan Liu, Sheng-hua Zhong, Wenjie Li*. Query-oriented multi-document summarization via unsupervised deep learning. In Proceedings of 26th AAAI International Conference on Artificial Intelligence (AAAI’ 12), 2012.
  • Sheng-hua Zhong,Yan Liu*, Yang Liu. Bilinear deep learning for image classification. In Proceedings of 19th ACM International Conference on Multimedia (SIG MM'11), 2011. (Qualcomm Award)
  • Yang Liu, Yan Liu*,Sheng-hua Zhong, Keith C. C. Chan. Semi-supervised manifold ordinal regression for image ranking. In Proceedings of 19th ACM International Conference on Multimedia (SIG MM'11), 2011.
  • Sheng-hua Zhong, Yan Liu*, Ling Shao, Gangshan Wu. Unsupervised saliency detection based on 2D Gabor and Curvelets transforms. In Proceedings of 3rd ACM International Conference on Internet Multimedia Computing and Service (ACM ICIMCS'11), 2011.
  • Sheng-hua Zhong, Yan Liu*, Ling Shao, Fu-lai Chung. Water reflection recognition via minimizing reflection cost based on motion blur invariant moments. In Proceedings of 1st ACM International Conference on Multimedia Retrieval (ICMR'11), 2011.
  • Sheng-hua Zhong,Yan Liu*, Yang Liu, Fu-lai Chung. Fuzzy-based contextual Cueing for region-level annotation. In Proceedings of 2nd ACM International Conference on Internet Multimedia Computing and Service (ACM ICIMCS'10), 2010. (Best Paper Award).
  • Sheng-hua Zhong,Yan Liu*, Yang Liu, and Fu-lai Chung. A semantic no-reference image sharpness metric based on top-down and bottom-up saliency map modeling. In Proceedings of 17th IEEE International Conference on Image Processing (ICIP'10), 2010.
Research Institute for Future Media Computing,Shenzhen University 2014 - 2017