Find Us On:

Twitter
Facebook
RSS
YouTube
Linked In

 

Join Our Mailing List

 

We won't spam you or ever share your information.

Shenghua Gao

Profile Text
Shenghua Gao
Former Researcher
 

Shenghua Gao was a researcher at ADSC. He worked on robust object and face recognition. He had his PhD study in Nanyang Technological University, Singapore. Before that, he received B. Eng from University of Science and Technology of China (Outstanding Graduates). His research interests can be broadly categorized into two areas: computer vision and machine learning. Currently he is focusing on exploiting the data structure for robust object and face recognition. He was awarded Microsoft Research Fellowship in 2010.

Research Interests:

  • Computer Vision: Object Recognition, Face recognition, Segmentation, Saliency detection, etc.
  • Machine Learning: Subspace Learning,  Lowrank/Sparse techniques, Deep Learning, etc.

ADSC Project:

Education:

  • Nanyang Technological University (NTU), Singapore
    • PhD Candidate in Computer Engineering, Aug 2008 – June 2012
  • University of Science and Technology of China (USTC), Hefei, China
    • B.Eng. in Electronic Engineering and Information Science, Sep 2004 – Jun 2008
    • Outstanding Graduates in USTC.

Experience:

  • Advanced Digital Sciences Center, Singapore June 2012 – Present
    • Project: Robust object and face recognition
  • Nanyang Technological University, Singapore Aug 2008 – June 2012
    • Thesis Title: Improving sparse coding with graph, kernel, and  structure
  • MOE-Microsoft Key Laboratory of Multimedia Computing and Communication, USTC, China  Feb 2008 – Jun 2008
    • Final Year Project : Pedestrian detection
  • Institute of Automation, Chinese Academy of Sciences, Beijing, China  Jul 2007 – Sep 2007
    • Summer Intern : Handwriting extraction.
  • School of Information Science and Technology, USTC, China  Aug 2006 – Oct 2006
    • Undergraduate Research Project : USTC RoboGame Contest (Champion).

Publications and Patents:

Journal papers:

  1. Shenghua Gao, Ivor Wai-Hung Tsang and Liang-Tien Chia. Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and Applications. To appear on IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  2. Zhixiang Ren, Shenghua Gao, Liang-Tien Chia, Deepu Rajan and Yun Huang. Sparse Representation for Saliency Detection. (In submission to TIP. 2nd round review.)
  3. Qi Mao, Ivor Wai-Hung Tsang, Shenghua Gao. Objective-Guided Image Annotation. In submission to TIP.
  4. Shenghua Gao*, Zhixiang Ren*, Liang-Tien Chia and Ivor Wai-Hung Tsang. Region Based Saliency Detection and Its application in Object Recognition, submitted IEEE Transactions on Multimedia (TMM). (* indicates equal contributions. In 3rd round review.)
  5. Shenghua Gao, IvorWai-Hung Tsang and Liang-Tien Chia. Sparse Representation with Kernels, To appear IEEE Transactions on Image Processing (TIP).
  6. Shenghua Gao, Liang-Tien Chia and Xiangang Cheng. Web Image Concept Annotation with Better Understanding of Tags and Visual Features. Journal of Visual Communication and Image Representation (JVCIR). Volume 21 Issue 8, Pages 806-814, November, 2010.

Conference papers:

  1. Zhengxiang Wang, Shenghua Gao, Liang-Tien Chia. Learning Class-to-Image Distance via Large Margin and L1-norm Regularization. The 12th European Conference on Computer Vision (ECCV 2012), Italy, 2012
  2. Zhixiang Ren, Shenghua Gao, Liang-Tien Chia, Deepu Rajan and Yun Huang. SpatioTemporal Saliency Detection Via Sparse Representation. IEEE International Conference on Multimedia & Expo (ICME) 2012 (Oral)
  3. Shenghua Gao, Liang-Tien Chia and Ivor Wai-Hung Tsang. Multi-layer Group Sparse Coding - for Concurrent Image Classification and Annotation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs, Colorado, June 2011.
  4. Shenghua Gao, Zhengxiang Wang, Liang-Tien Chia and Ivor Wai-Hung Tsang. Automatic Image Tagging via Category Label and Web Data. Proceedings of the ACM International Conference on Multimedia (ACM Multimedia 2010), Firenze, Italy, October, 2010.
  5. Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia. Kernel sparse representation for image classification and face recognition. The 11th European Conference on Computer Vision (ECCV 2010),Crete, Greece, 2010.
  6. Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia and Peilin Zhao. Local features are not lonely–laplacian sparse coding for image classification. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2010), San Francisco, USA, 2010.
  7. Shenghua Gao, Xiangang Cheng, Liang-Tien Chia. Discovering class-specific informative patches for landmark characterization. International Multimedia Modeling Conference (MMM), Chongqing, China, 2010. (oral)
  8. Huan Wang, Liang-Tien Chia, and Shenghua Gao. Wikipedia-assisted concept thesaurus for better web media understanding. Multimedia Information Retrieval (MIR), Philadelphia, Pennsylvania,2010.
  9. Shenghua Gao, Liang-Tien Chia and Xiangang Cheng. Understanding tag-cloud and visual features for better annotation of concepts in nus-wide dataset. ACM MM workshop on web-scale multimedia corpus, Beijing, China, 2009.(oral)
  10. Shenghua Gao, Xiangang Cheng, Huan Wang and Liang-Tien Chia. Concept model-based unsupervised web image re-ranking. International Conference on Image Processing (ICIP), Carol, Egypt, 2009. (oral)

Awards:

  • Microsoft Research Fellowship, 2010
  • Graduate Research Scholarship of NTU, 2008-2012
  • Outstanding Graduates in USTC, 2008
  • National Encouragement Scholarship in China, 2007
  • 2nd Prize in Anhui Province, China Undergraduate Mathematical Contest in Modeling (CUMCM), 2007
  • Champion of USTC RoboGame Contest, 2006(Team Captain)
  • Outstanding Student Scholarship in USTC, 2004,2005,2006,2007