Electronic Engineering Department, The Chinese University of Hong Kong - Prof WANG, Xiaogang 王曉剛

Homepage

Professor
BSc(USTC), MPhil(CUHK), PhD(MIT)
homepage Rm 415, Ho Sin Hang Engineering Building phone Tel: +852 3943 8283 This email address is being protected from spambots. You need JavaScript enabled to view it.

Research Interests:

Crowd behaviour analysis, Object detection and tracking, Person re-identification, Face recognition, Image and video searching, Medical imaging

 

hyperlink http://www.ee.cuhk.edu.hk/~xgwang/

Research Highlights

 

Resume of Career

Xiaogang Wang received his Bachelor degree in Electrical Engineering and Information Science from the Special Class of Gifted Young at the University of Science and Technology of China, MPhil. degree in Information Engineering from the Chinese University of Hong Kong, and PhD degree in Computer Science from Massachusetts Institute of Technology. He is an assistant professor in the Department of Electronic Engineering at the Chinese University of Hong Kong since August 2009. He was the Area Chair of IEEE International Conference on Computer Vision (ICCV) 2011. He received the Outstanding Young Researcher in Automatic Human Behaviour Analysis award in 2011, and Hong Kong Early Career Award in 2012.

His research interests include computer vision, pattern recognition, machine learning, and applications to visual surveillance, face recognition, image and video searching, and medical imaging.

Current Research Interests

Crowd behaviour analysis, Object detection and tracking, Person re-identification, Face recognition, Image and video searching, Medical imaging

Highlights of Recent Research Achievements

  • Prof. Wang's group is among the first to start research on vision-based crowd behaviour analysis. At 2007, Prof. Wang published the first nonparametric hierarchical Bayesian model to automatically learn crowd behavior models from local motions without detecting or tracking objects and without supervision. At CVPR 2012, Prof. Wang's group proposed the first agent-based model to learn collective dynamics, and model crowd behaviours at both macroscopic and microscopic levels. At CVPR 2013, Prof. Wang's group published the first work on measuring the collectiveness of crowds from video sequences, which has wide applications to video surveillance, crowd management and crowd video retrieval.
  • Occlusion is a severe problem in crowd video surveillance. Prof. Wang's group proposed hierarchical deep models, and single-pedestrian detection aided by multi-pedestrian detection for occlusion handling. They have achieved the highest pedestrian detection accuracy on three major public benchmark datasets: Caltech, ETH and TUD-Brussels.
  • Prof. Wang's group proposed the first transfer learning framework of automatically transferring a generic pedestrian detector to a scene specific detector without manually labeling any training samples from the target scene. It largely improves the detection accuracy by more than 40% on multiple benchmark datasets.
  • Prof. Wang received three GRF/ECS after joining CUHK for three years. The total amount of research grants secured by this group exceeds 5 million Hong Kong dollars.
  • Prof. Wang received the Hong Kong Early Career Award 2012. There are 19 awardees out of 300 applicants in Hong Kong. CUHK has 6 awardees.
  • Prof. Wang's research works have more than 2000 citations in Google Scholar with an h-index of 21. His profile at Google Scholar can be found at http://scholar.google.com/citations?user=-B5JgjsAAAAJ&hl=en

Taught Courses

  • Pattern Recognition
  • Image Processing and Video Technology
  • Biomedical Imaging Applications
  • Problem Solving by Programming
  • Engineering Design
  • Basic Circuit Theory

Honors and Awards

  • Hong Kong RGC Early Career Award 2012.
  • Outstanding Young Researcher in Automatic Human Behaviour Analysis award in 2011. The Award is sponsored by the European Research Council Starting Grant agreement no. ERC-2007-StG-203143 (MAHNOB) and is administered by the Awards Committee of the CVPR4HB Workshop Organization.

External Service in Recent 3 Years

  • Area Chair of IEEE International Conference on Computer Vision (ICCV) 2011.
  • Associate Editor of Image and Visual Computing Journal.

Publications for the Past 3 Years

    1. X. Tang, K. Liu, J. Cui, F. Wen and X. Wang, 'IntentSearch: Capturing User Intention for One-Click Internet Image Search,' IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 34, pp. 1342-1353, 2012.

    2. W. Ouyang and X. Wang, 'A Discriminative Deep Model for Pedestrian Detection with Occlusion Handling,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR), 2012.

    3. M. Wang, W. Li and X. Wang, 'Transferring a Generic Pedestrian Detector Towards Specific Scenes,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR), 2012.

    4. B. Zhou, X. Tang and X. Wang, 'Understanding Collective Crowd Behaviors: Learning Mixture Model of Dynamic Pedestrian-Agents,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2012. (oral)

    5. P. Luo, X. Wang and X. Tang, 'Hierarchical Face Parsing via Deep Learning,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2012.

    6. W. Luo, F. Lu, X. Wang and X. Tang, 'Synthesizing Oil Painting Surface Geometry from a Single Photograph,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2012.

    7. P. Luo, X. Wang, L. Liang, and X. Tang, 'Joint Semantic Segmentation by Searching for Compatible-Competitive References,' in Proceedings of ACM Multimedia, 2012.

    8. X. Wu, Y. Qiao, X. Wang and X. Tang, 'Bridging Music and Image: A Preliminary Study with Multiple Ranking CCA Learning,' in Proceedings of ACM Multimedia, 2012.

    9. B. Zhou, X. Tanng and X. Wang, 'Coherent Filtering: Detecting Coherent Motions from Crowd Clutters,' in Proceedings of European Conference on Computer Vision (ECCV), 2012.

    10. W. Zhang, X. Wang, D. Zhao, and X. Tang, 'Graph Degree Linkage: Agglomerative Clustering on a Directed Graph,' in Proceedings of European Conference on Computer Vision (ECCV), 2012.

    11. W. Li, R. Zhao, and X. Wang, 'Human Reidentification with Transferred Metric Learning,' in Proceedings of Asian Conference on Computer Vision (ACCV), 2012. (oral)

    12. X. Wang, K. Ma, G. Ng, and E. Grimsion, 'Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models,' International Journal of Computer Vision (IJCV), Vol. 96, pp. 287-321, 2011.

    13. X. Wang, E. Grimson and C. F. Westin, 'Tractography Segmentation Using a Hierarchical Dirichlet Processes Mixture Model,' NeuroImage, Vol. 54, pp. 290-302, 2011.

    14. C. Zhao, X. Wang and W. Cham, 'Background Subtraction via Robust Dictionary Learning,' EURASIP Journal on Image and Video Processing, 2011.

    15. W. Luo, X. Wang, and X. Tang, 'Content-Based Photo Quality Assessment,' in Proceedings of IEEE International Conference on Computer Vision (ICCV) 2011.

    16. K. Jia, X. Wang, and X. Tang, 'Optical Flow Estimation Using Learned Sparse Model,' in Proceedings of IEEE International Conference on Computer Vision (ICCV) 2011.

    17. X. Wang, K. Liu and X. Tang, 'Query-Specific Visual Semantic Spaces for Web Image Re-ranking,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2011.

    18. M. Wang and X. Wang, 'Automatic Adaption of a Generic Pedestrian Detector to a Specific Traffic Scene,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2011.

    19. W. Zhang, X. Wang and X. Tang, 'Coupled Information-Theoretic Encoding for Face Photo-Sketch Recognition,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2011. (oral)

    20. B. Zhou, X. Wang and X. Tang, 'Random Field Topic Model for Semantic Region Analysis in Crowded Scenes from Tracklets,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2011.

    21. C. Zhao, X. Wang and W. Cham, 'Joint Face Alignment with a Generic Deformable Face 'Model,' in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR) 2011.

    22. B. Gong, J. Liu, X. Wang, and X. Tang, '3D Object Retrieval with Semantic Attributes,' in Proceedings of ACM Multimedia, 2011.

    23. C. Li, X. He, V. Mok, W. Chu, J. Yuan, Y. Sun and X. Wang, 'Free-Form Fibers: A Whole Brain Fiber-to-DTI Registration Method,' in Proceedings of Workshop on Computational Diffusion MRI, 2011.

    24. X. Wang, 'Action Recognition Using Topic Models,' in the book of "Visual Analysis of Humans: Looking at People," edited by Thomas B. Moeslund, Adrian Hilton, Volker Kruger, and Leonid Sigal, published by Springer, 2011.

    25. X. Wang, 'Semantic Object Segmentation,' in the book of 'Video Segmentation and Its Applications', edited by King N. Ngan and Hongliang Li, published by Springer, 2011.

    26. X. Wang, K. Tieu, and W. E. L. Grimson, 'Correspondence-Free Activity Analysis and 'Scene Modeling in Multiple Camera Views,' IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 32, pp. 56-71, 2010.

    27. W. Zhang, X. Wang and X. Tang, 'Lighting and Pose Robust Face Sketch Synthesis,' in Proceedings of European Conference on Computer Vision (ECCV), 2010.

 

 

back-to-top