Zhen Cui (崔振)

Associate Professor, Ph.D.,

Affective Information Processing Lab,

Key Laboratory of Child Development and Learning Science of Ministry of Education,

Research Center for Learning Science,

Southeast University, Nanjing, China.

  

Email: zhen.cui@seu.edu.cn

URL: aip.seu.edu.cn/zcui/

Office: Room 318(Middle), Liwenzheng Building, Southeast University, No. 2 Sipailou, Nanjing, P.R. China.


[BIOGRAPHY]  [EDUCATION]  [WORK EXPERIENCE]  [RESEARCH FOCUS]  [PUBLICATIONS]

[CODES]  [PATENTS]  [RESEARCH PROJECTS]  [HONORS]  [SERVICES]


  

BIOGRAPHY


Received the Ph.D. degree in computer science from Institute of Computing Technology (ICT), Chinese Academy of Science (CAS), Beijing, in Jun. 2014. He was a Research Fellow in the Department of Electrical and Computer Engineerning at National University of Singapore (NUS) from Sep. 2014 to Nov. 2015. He also spent half a year as a Research Assistant on Nanyang Technological University (NTU) from Jun. 2012 to Dec. 2012. Now he is an Associate Professor of Southeast University, China. His research interests cover computer vision, pattern recognition and machine learning, especially focusing on deep learning, manifold learning, sparse coding, face detection/alignment/recognition, object tracking, image super resolution, emotion analysis, etc.

   

EDUCATION


Chinese Academy of Sciences, Beijing, China

Ph.D. student, Computer Science

Sep. 2009 – June 2014

Sun Yat-sen (Zhongshan) University, Guangzhou, China

M.S., Computer Software and Theory

Sep. 2004 – July 2006

Shandong Normal University, Jinan, China

B.S., Computer Science

Sep. 2000 – July 2004

   

WORK EXPERIENCE


National University of Singapore, Singapore

Research Fellow (Postdoc.)

Sep. 2014 – Nov.2015

Nanyang Technological University, Singapore

Research Assistant

Jun 2012 -Dec. 2012

Huaqiao University, Xiamen, Fujian, China

Teacher, Lecturer

July 2006 – Mar. 2016

Southeast University, Nanjing, Jiangshu, China Teacher, Associate Professor April 2016 – Present

   

RESEARCH FOCUS


Cover computer vision, pattern recognition and machine learning. Especially focus on manifold learning, sparse coding, deep learning, and their applications in face detection/alignment/recognition, object tracking/classification, super resolution and emotion analysis.

   

PUBLICATIONS

  1. Yan Li, Ruiping Wang, Zhen Cui, Shiguang Shan, and Xilin Chen. Spatial Pyramid Covariance based Compact Video Code for Robust Face Retrieval in TV-series, IEEE Transactions on Image Processing (T-IP), 2016.
  2. Jingwei Yan, Wenming Zheng*, Zhen Cui*, Chuangao Tang, Tong Zhang, Yuan Zong and Ning Sun. Multi-Clue Fusion for Emotion Recognition in the Wild. ACM International Conference on Multimodal Interaction (ICMI), 2016.
  3. Tong Zhang, Wenming Zheng, Zhen Cui, Yuan Zong, Jingwei Yan, Keyu Yan, “A Deep Neural Network Driven Feature Learning Method for Multi-view Facial Expression Recognition”, IEEE Transactions on Multimedia (T-MM), 2016.
  4. Youyi Cai, Wenming Zheng, Tong Zhang, Qiang Li, ,Zhen Cui, Jiayin Ye, “Video Based Emotion Recognition Using CNN and BRNN“, in Chinese Conference on Pattern Recognition, 2016.
  5. Yang Li, Wenming Zheng* and Zhen Cui*. A Novel Graph Regularized Sparse Linear Discriminant Analysis Model for EEG Emotion Recogntion, The 23rd of International Conference on Neural Information Processing (ICONIP), 2016.
  6. Keyu Yan, Wenming Zheng* and Zhen Cui*. Cross-Database Facial Expression Recognition via Unsupervised Domain Adaptive Dictionary Learning. The 23rd of International Conference on Neural Information Processing (ICONIP), 2016.
  7. Yuan Zong, Wenming Zheng, Zhen Cui and Qiang Li. Double Sparse Learning Model for Speech Emotion Recognition, Electronics Letters, 2016.
  8. Zhen Cui, Zhiheng Niu, Luoqi Liu and Shuicheng Yan. Layerwise class-aware convolutional neural network. IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2016.
  9. Wei Wang, Zhen Cui, Yan Yan, Xiangbo Shu, Jiashi Feng, Shuicheng Yan and Nicu Sebe. Deeply Face Aging. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (Oral)

  10. Zhen Cui, Shengtao Xiao, Jiashi Feng and Shuicheng Yan. Recurrently Target-Attending Tracking. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 
  11. Bineng Zhong, Xiangnan Yang, Yingju Shen, Cheng Wang, Tian Wang, Zhen Cui*, etl. Higher Order Partial Least Squares for Object Tracking: A 4d-Tracking Method, Neurocomputing, 2016.

  12. Zhen Cui, Hong Chang, Shiguang Shan, and Xilin Chen. Generalized Unsupervised Manifold Alignment. Neural Information Processing Systems Foundation (NIPS), 2014.
  13. Kongming Liang, Hong Chang, Zhen Cui, Shiguang Shan, Xilin Chen. Representation Learning with Smooth Autoencoder. The12th Asian Conference on Computer Vision (ACCV), 2014.
  14. Xin Liu, Bineng Zhong, Maosheng Zhang, Zhen Cui, Motion Saliency Extraction via Tensor Based Low-rank Recovery and Block-sparse Representation, Journal of Computer-Aided Design & Computer Graphics, No. 10, 2014. (In Chinese)
  15. Yan Li, Ruiping Wang, Zhen Cui, Shiguang Shan, Xilin Chen. Compact Video Code and Its Application to Robust Face Retrieval in TV-Series. The25th British Machine Vision Conference (BMVC), 2014.
  16. Zhen Cui, Hong Chang, Shiguang Shan, Bineng Zhong and Xilin Chen. Deep Network Cascade for Image Super-resolution. European Conference on Computer Vision (ECCV), 2014.
  17. Xin Liu, Yiu-ming Cheung, Shujuan Peng, Zhen Cui, Bineng Zhong, Jixiang Du. Automatic motion capture data denoising via filtered subspace clustering and low rank matrix approximation. Signal Processing, 105: 350-362, Dec.2014.
  18. Zhen Cui, Shiguang Shan, Ruiping Wang, Lei Zhang, and Xilin Chen. Sparsely Encoded Local Descriptor for Face Verification, Neurocomputing, volume 147: 403-411, Jan, 2015.
  19.  Bineng Zhong, Yingju Shen, Yan Chen, Weibo Xie, Zhen Cui, etc. Online Learning 3D Context for Robust Visual Tracking. Neurocomputing, 151:710-718, March, 2015.
  20.  Wen Wang, Zhen Cui, Hong Chang, Shiguang Shan and Xilin Chen. Deeply Coupled Auto-encoder Networks for Cross-view Classification. arXiv:1402.2031.
  21.  Zhen Cui, Shiguang Shan, and Xilin Chen. Structured Sparse linear discriminant Analysis, Journal of Computer Research and Development. 51(10): 2295-2301, 2014. (in Chinese).
  22.  Zhen Cui, Hong Chang, Shiguang Shan, Bingpeng Ma, and Xilin Chen. Joint Sparse Representation for Video-based Face Recognition, Neurocomputing. 135:306-312, July, 2014.
  23.  Zhen Cui, Wen Li, Dong Xu, Shiguang Shan, Xilin Chen, and Xuelong Li. Flowing on Riemannian Manifold: Domain Adaptation by Shifting Covariance, IEEE Transactions on Cybernetics (T-cyb). 44(12):2264 – 2273, 2014.
  24.  Bineng Zhong, Xiaotong Yuan, Rongrong Ji, Yan Yan, Zhen Cui, etc. Structured partial least squares for simultaneous object tracking and segmentation, Neurocomputing, 133:317-327, June, 2014.
  25. Zhen Cui, Wen Li, Dong Xu, Shiguang Shan, Xilin Chen. Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2013, 3554-3561.
  26. Zhen Cui, Shiguang Shan, Haihong Zhang, Shihong Lao, and Xilin Chen. Structural Sparse Linear Discriminant Analysis. International Conference on Image Processing (ICIP), 2012, 1161-1164. (oral)
  27.  Zhen Cui, Shiguang Shan, Haihong Zhang, Shihong Lao, and Xilin Chen. Image Sets Alignment for Video-based Face Recognition, IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2012, 2626-2633.
  28.  Zhen Cui, Shiguang Shan, Xilin Chen, Lei Zhang. Sparsely Encoded Local Descriptor for Face Recognition. The Ninth IEEE International Conference on Automatic Face and Gesture Recognition (FGR), 2011, 149-154.

 * Correspondence author

 

CODES/RESULTS

  • Face Region Descriptor & Multiple Metric Learning. Codes.
    • (Zhen Cui, Wen Li, Dong Xu, Shiguang Shan, Xilin Chen. Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2013, 3554-3561.)
  • Recurrent Shape Regression. Codes, 300-W Results. 
    • (Zhen Cui, Shengtao Xiao, Zhiheng Niu, Shuicheng, Wenming Zheng, Recurrent Shape Regression, Underview)
  • Recurrently Target-Attending Tracking (RTT). Results on the benchmark [CVPR’13].
    • (Zhen Cui, Shengtao Xiao, Jiashi Feng, Shuicheng Yan. Recurrently Target-Attending Tracking. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016)


PATENTS


[1] Xilin Chen, Xiujuan Chai, Zhen Cui, Bin Wu, Yuan Zheng, Haifeng Chen. Fast classification and relevant devices for glass image defects. No. CN201010266615.0, Mar, 2011.

[2] Xilin Chen, Xiujuan Chai, Bin Wu, Zhen Cui,Yuan Zheng, Haifeng Chen. Robust detection and relevant devices for scratched glass image. No. CN201010266622.0, Mar, 2011.

   

RESEARCH PROJECTS


[1] Sparse manifold modeling and its application to video-based face recognition. (NSFC:No. 61202297, 2013/01-2015/12) PI

[2] Face recognition from low-quality videos. (Natural Science Foundation of Fujian Province:No.2013J01239, 2013/01-2015/12) PI

[3] Joint Representation and Processing of Clustering Image / Video. (Major Program of NSFC, No. 61390511, 2014/01-2018/12)

   

HONORS


Received the excellent PH.D. thesis of CAS in 2015.

   

SERVICES


2016, Reviewer of NIPS.

2015, Reviewer of CVPR.

2014, Reviewer of ACM Multimedia.

2015, PC member of the 10th Chinese Conference on Biometric Recognition(CCBR2015).

2014, PC member of the 9th Chinese Conference on Biometric Recognition(CCBR2014).

2013, PC member of the 8th Chinese Conference on Biometric Recognition(CCBR2013).

2013, Reviewer of CVPR.

2013, Reviewer of ICIP.

Reviewer of TPAMI, TNNLS, TMM, TIP, TCSVT, Neurocomputing, Journal of Computer Research and Development, Machine Vision and Applications.

FRD – Released Code & ROCFRD – Released Code & ROCresults