Dongshun Cui has obtained his Bachelor degree in Engineering from South China University of Technology in 2012, and his supervisors are Shaolin Zhou and Xiangmin Xu. He has obtained his Master degree in Engineering from Beijing Institute of Technology in 2015, and his supervisors are Baojun Zhao, Linbo Tang, and Chenwei Deng. He has been a full-time Ph.D. student at Nanyang Technological University since Jan. 2015 and will graduate before Dec. 2018. His supervisors are Guang-Bin Huang, Jie Zhang, and Zhiping Lin.

Find my CV here: CV-CuiDongshun.pdf.
Find more personal information about me here: My Linkedin, 中文主页.
Find more personal projects of me here: My YouTube.

Reviewers of:

• [Journal (Elsevier)] Neural Networks [2017 IF=7.197],
• [Journal (Elsevier)] Signal Processing [2017 IF=3.470],
• [Journal (Elsevier)] Neurocomputing [2017 IF=3.241],
• [Journal (Elsevier)] Multidimensional Systems and Signal Processing [2017 IF=2.088],
• [Journal (Springer)] Cognitive Computation [2017 IF=3.479],
• [Journal (Springer)] Soft Computing [2017 IF=2.367],
• [Journal (SPIE)]Journal of Electronic Imaging [2017 IF=0.780],
• [Conference (IEEE)] International Joint Conference on Neural Networks,
• [Conference (Springer)] International Conference on Extreme Learning Machine.

2017, Outstanding Contribution in Reviewing Awarded by Neurocomputing.
2017, Recognized Reviewer of Signal Processing.
2016, Recognized Reviewer of Neurocomputing.
2015, Full Research Scholarship.
2014, National Scholarship for Graduate Students.
2014, Outstanding Graduate in Beijing Institute of Technology (Personal Highest Honor (~1‰)).
2012, Excellent Freshman Scholarship of Beijing Institute of Technology.
2011, Excellent Student in South China University of Technology.
2010, Excellent Volunteer in Guangzhou Asian Games.
2009, Third-class Scholarship of South China University of Technology.

1. ELM based Smile Detection using Distance Vector
   Dongshun Cui, Guang-Bin Huang, Tianchi Liu. Pattern Recognition: 2018. [2016 IF=4.582] Abstract  The Smile is one of the most common facial expressions, and it serves as an indicator of the positive emotion. Many feature extraction methods have been proposed for detecting a smile in an unconstrained scene. However, most of the existing feature descriptors are too large and not effective to be applied to distinguish smile and non-smile in the real world. In this paper, we proposed an ELM-based smile detection system by using a novel feature extraction method. Motivated by the observation that the mouth shape can effectively reflect a person’s smile state, a novel and snappy set of features from a few of facial landmarks around the mouth are extracted. We have tested our algorithms on the smile detection database, and the results indicate that our method is better than the state-of-the-art methods with higher accuracy and lower dimension of features.
2. Face recognition using total loss function on face database with ID photos
   Dongshun Cui, Guanghao Zhang, KaiHu, Wei Han, Guang-Bin Huang. Optics & Laser Technology: 2017. [2016 IF=2.109] Abstract  With the development of deep neural networks, researchers have developed lots of algorithms related to face and achieved comparable results to human-level performance on several databases. However, few feature extraction models work well in the real world when the subject which is to be recognized has limited samples, for example, only one ID photo can be obtained before the face recognition task. To our best knowledge, there is no face database which contains ID photos and pictures from the real world for a subject simultaneously. To fill this gap, we collected 100 celebrities’ ID photos and their about 1000 stills or life pictures and formed a face database called FDID. Besides, we proposed a novel face recognition algorithm and evaluated it with this new database on the real-life videos.
3. Deformable and Occluded Object Tracking via Graph Learning
   Wei Han, Guang-Bin Huang and Dongshun Cui. The International Conference on Digital Image Computing: Techniques and Applications (DICTA): 2017, 1-8. Abstract  To Be Added.
4. Compact Feature Representation for Image Classification Using ELMs
   Dongshun Cui, Guanghao Zhang, Wei Han, Liyanaarachchi Lekamalage Chamara Kasun, Kai Hu and Guang-Bin Huang. The IEEE International Conference on Computer Vision (ICCV) Workshops: 2017, 1015-1022. [Premium Conferences] Abstract  Feature representation/learning is an essential step for many computer vision tasks (like image classification) and is broadly categorized as 1) deep feature representation; 2) shallow feature representation. With the development of deep neural networks, many deep feature representation methods have been proposed and obtained many remarkable results. However, they are limited to real-world applications due to the high demand for storage space and computation ability. In our work, we focus on shallow feature representation (like PCANet) as these algorithms require less storage space and computational resources. In this paper, we have proposed a Compact Feature Representation algorithm (CFR-ELM) which consists of compact feature learning module and a post-processing module. We have tested CFR-ELM on four typical image classification databases, and the results demonstrate that our method outperforms the state-of-the-art methods.
5. Target Coding for Extreme Learning Machine
   Dongshun Cui, Kai Hu, Guanghao Zhang, Wei Han, Guang-Bin Huang. Proceedings of ELM-2017. Springer: 2017. [In Press] Abstract  [To be added.]
6. Aviation Guide Gesture Recognition Using ELM with Multiscale CNN Features
   Xiangyang Deng, Zhenyu Li, Dongshun Cui, Jiawen Feng. Proceedings of ELM-2017. Springer: 2017. [In Press] Abstract  [To be added.]
7. Face Recognition Benchmark with ID Photos
   Dongshun Cui, Guanghao Zhang, Kai Hu, Wei Han and Guang-Bin Huang. International Symposium on Artificial Intelligence and Robotics (ISAIR), Springer.: 2017, 27-35. Abstract  [To Be Added.]
8. Classification of Foreign Object Debris using Integrated Visual Features and Extreme Learning Machine
   Kai Hu, Dongshun Cui, Yuan Zhang, Chunhong Cao, Fen Xiao and Guang-Bin Huang CCF Chinese Conference on Computer Vision (CCCV). Springer.: 2017, 3-13. Abstract  [To Be Added.]
9. Stable and Improved Generative Adversarial Nets (GANs): A Constructive Survey
   Guanghao Zhang, Enmei Tu and Dongshun Cui. International Conference on Image Processing (ICIP), IEEE.: 2017, 1871-1875. [Premium Conferences] Abstract  [To be added.]
10. Multi Layer Multi Objective Extreme Learning Machine
    L.L. Chamara Kasun, Kang Song, Guang-Bin Huang, Dongshun Cui and Ken Liang. International Conference on Image Processing (ICIP), IEEE.: 2017, 1297-1301. [Premium Conferences] Abstract  [To be added.]
11. ELMNet: Feature Learning using Extreme Learning Machines
    Dongshun Cui, Guang-Bin Huang, L.L. Chamara Kasun, Guanghao Zhang and Wei Han. International Conference on Image Processing (ICIP), IEEE.: 2017, 1857-1861. [Premium Conferences] Abstract  [To be added.]
12. Smile detection using Pair-wise Distance Vector and Extreme Learning Machine
    Dongshun Cui, Guang-Bin Huang, Tianchi Liu. Neural Networks (IJCNN), 2016 International Joint Conference on.: 2016, 2298-2305. [Premium Conferences] Abstract  A smile is a common human facial expression used as the indicator for positive emotion. The detection of smiling has many applications, for example, controlling camera shutter when a smile is detected and measuring the degree of satisfaction during a video conference. Many feature extraction methods have been proposed for detecting a smile in the unconstrained scenarios. However, the dimensions of most existing feature descriptors are too huge, which limits their real applications. Moreover, features should be more effective to distinguish between smile face and non-smile face. Motivated by the observation that the mouth shape can effectively reflect a persons smile state, we extracted a novel and snappy set of features that form a feature vector named Pair-wise Distance Vector, which is calculated only based on few points around a mouth. After that, Extreme Learning Machine (ELM) is adopted to classify smile based on these features. The experimental results on GENKI-4K database show that our proposed method outperforms the state-of-the-art methods in terms of accuracy and dimension of features.
13. Two-stage structured learning approach for stable occupancy detection
    Tianchi Liu, Yue Li, Zuo Bai, Jaydeep De, Cao Vinh Le, Zhiping Lin, Shih-Hsiang Lin, Guang-Bin Huang, Dongshun Cui. Neural Networks (IJCNN), 2016 International Joint Conference on.: 2016, 2306-2312. [Premium Conferences] Abstract  Monitoring the presence of occupants in a room in a timely manner is a fundamental step for effective building management. Environmental sensor networks have the advantages of high cost-efficiency and non-intrusiveness on privacy and are very suitable for room occupancy detection. Nonlinear discriminative models, e.g., support vector machine and neural networks, have shown good detection performance due to their ability to model complex relationship. However, they tend to produce unstable detection with frequent fluctuations over time, because they regard training data as independent and ignore the prior knowledge of the room occupancy, i.e., not changing very frequently. To improve the stability of the detection, we propose a two-stage structured learning approach with Extreme Learning Machine (ELM) as the local classifier. In the first stage, ELM is used as a fast nonlinear classifier to obtain preliminary detection results. In the second stage, we form data sequences consisting of the current and previous data points. The preliminary detection results by ELM of the data sequences are then used as input to a linear support vector machine for structured output to generate the final detection results. We test the proposed two-stage structured learning approach on a real-world dataset and show that the proposed approach outperforms the related machine learning methods.
14. A Perceptual Image Quality Assessment Metric Using Singular Value Decomposition
    Shuigen Wang, Dongshun Cui, Baoxian Wang, Baojun Zhao and Jinglin Yang. Circuits, Systems, and Signal Processing: 2015, 34, 209-229. [2016 IF=1.694] Abstract  Image distortion can be categorized into two types: content-dependent degradation and content-independent one. Most of the existing perceptual full-reference image quality assessment (IQA) metrics cannot deal with both these two different impacts well. Singular value decomposition (SVD) as a useful mathematical tool that has been used in various image processing applications (e.g., feature extraction). In this paper, SVD is employed to decompose the images into the structural (content-dependent) and the content-independent components. For each portion, a specific assessment model is designed to tailor for its corresponding distortion properties. All the proposed models are then fused to obtain a final quality score by extreme learning machine (ELM), a machine learning technique. Extensive experimental results on six publicly available databases demonstrate that the proposed metric achieves better performance in comparison with the relevant state-of-the-art quality metrics.
15. Robust Bridge Detection Over Water For Optical Images
    Dongshun Cui, Chenwei Deng, Shuigen Wang and Baojun Zhao. International Conference on Computational and Information Sciences: 2014, 4, 1103-1109. Abstract  State-of-the-art bridge detection methods in optical images share a common two-stage process: water segmentation followed by bridge extraction. These methods are usually based upon the extraction of parallel-line features in the water region, which is heavily affected by edge detection accuracy. Different from the existing methods, we proposed a robust bridge detection algorithm by exploiting the unique property of bridge corners. The pixel-level features of bridge corner across water and riverside regions are more stable than the parallel-line features, as line detection is more sensitive to noise. Experimental results with satellite images from Google Earth demonstrate that the proposed method achieves better performance.

Please download Face Database with ID Photos (FDID) database from Baidu Yun, and the password is "zeif". More details about this database will be added later.

2017 Impact Factors of Journals: 2017-IF.pdf [Collected from the Internet].

2017 Premium Conferences: Premium Conferences.pdf [Collected from NTU-EEE].

---

Useful Materials:

• How to write a good CVPR paper [link].

• TextBox, Tutorials

Email: cuidongshun@gmail.com