Zhiyong WANG  PhD (HKPU) MEng, BEng (SCUT

Senior Lecturer, Associate Director of Multimedia Lab
School of Information Technologies, The University of Sydney
  

Contact

Room 349 (East Wing)
School of IT Building, J12
phone: (+61) 02 9351 3766
Fax: (+61) 02 9351 3838
Email: zhiyong.wang at sydney.edu.au  

Mailing Address

School of Information Technologies
School of IT Building, J12
The University of Sydney
NSW 2006, Australia  

Multimedia Computing, Computing Fun!


We welcome highly self-motivated students who are interested in pursuing research study or conducting projects on multimedia computing with us.


Dr Wang joined the School of Information Technologies, the University of Sydney as Postdoctoral Research Fellow after his PhD study. Since then, he has endeavoured to strengthen both research and teaching on multimedia computing in the university. He is a key member of the BMIT (Biomedical and Multimedia Information Technology) research group. His research has created great impact in a number of fields such as multimedia search and data mining, human computer interaction, remote sensing, and traditional Chinese Medicine. He has been PC/TPC member of a number of prestieious conferences and regular reviewer of top conferences and journals such as IEEE Transactions. He is a member of IEEE.

Research Interets

Multimedia information processing, retrieval, and management
Mobile and Internet-based multimedia computing and mining
Human centred multimedia computing
Pattern recognition and machine learning

Teaching

2013

COMP5114 Digital Media Fundamentals (Semester 2)
D. Oung, L. Chen, and
W. Liu
E. Ingleton, J. Lingad, and
S. Dyer
D. Kukic and D. Nguyen

COMP5114 Digital Media Fundamentals (Semester 1)
B. Feng, M. Liu, and X. Wang J. Wang W. Hua and X. Xu

COMP5425 Multimedia Storage, Retrieval, and Delivery
P. Jin and J. Yang A. Jankovic A. Chen, N. Tran, and R. Huang

2012

COMP5114 Digital Media Fundamentals (Semester 2)
S. Nielsen and J. Charters C. Browne X. Jiang and A. Li

COMP5114 Digital Media Fundamentals (Semester 1)
O. Fried K. C. Chan and Z. Li X. Chen and S. Duan

COMP5425 Multimedia Storage, Retrieval, and Delivery
N. Davies, A. Petrovic,
and A. Simonetta
M. de Ridder F. Macpherson and R. Han

2011

COMP5114 Digital Media Fundamentals (Semester 2)
N. Anam, M. Kraemer,
and H. Mostafavi
S. Halim K. Minamitani, K. Nguyen,
and C. Syquia

COMP5114 Digital Media Fundamentals (Semester 1)
D. Thilakanathan B. Tran O. Dias and C. Percival

COMP5425 Multimedia Storage, Retrieval, and Delivery
W.-H. Chen and
N. S. Takkallapati
Q. Chen and A. Medeiros C. Lloyd

2010

COMP5114 Digital Media Fundamentals
COMP5425 Multimedia Storage, Retrieval, and Delivery

2009

INFO1105 Data Structures
INFO1905 Data Structures (Advanced)
COMP5114 Digital Media Fundamentals
COMP5425 Multimedia Storage, Retrieval, and Delivery

2008 and before

SOFT1101 Software Development I
SOFT1901 Software Development I (Advanced)
INFO1105 Data Structures
INFO1905 Data Structures (Advanced)
MULT3018 Multimedia Interaction
MULT3306 Multimedia Computing and Processing
MULT3307 Interactive Multimedia System
COMP5114 Digital Media Fundamentals
COMP5211 Algorithms
COMP5415 Multimedia Authoring and Production
COMP5425 Multimedia Storage, Retrieval, and Delivery

Research on Multimedia

Multimedia information (i.e. image/video/audio) has greatly enriched our daily life, while the increasing computing power, storage capacity, bandwidth capacity, and more capable mobile devices such as smartphones make more and more multimedia contents and applications feasible. For instance, it has been much more convenient to take high quality photos, add special effects, and share them with friends and family instantly. Meanwhile it has been realized that multimedia information possesses more challenges than conventional information in terms of acquisition, processing, access, reusing, mining, and delivery. Innovative multimedia computing technologies, which play a crucial role in a wide range of application domains such as media industry, entertainment industry, scientific research, museum, Internet, mobile, social science, and healthcare, are highly demanded to further facilitate multimedia services and to more efficiently utilize multimedia information generated from diverse domains. Students involved in the projects will have the opportunity to access the world class and industry level facilities of the Multimedia Laboratory, and will be able to develop the necessary skills for the competitive job market.

Demo: video keyframe selection

Supervisors: Dr Zhiyong Wang and Prof David Feng

1. Multimedia Information Retrieval

With the proliferation of multimedia information, users being confronted with such information deluge have been actively looking for efficient and efficient multimedia information retrieval techniques. For example, almost everybody accumulates more and more photos and video footages and demands richer functionality on organizing such multimedia assets, such as showing photos of a family member in a specific occasion (e.g. birthday party), which cannot be easily handled by traditional print albums. This research project focuses on low-level feature extraction (e.g. color), content representation, similarity matching and ranking, semantic concept learning and annotation, indexing, scalable processing, summarization, user interaction, personalization, and user interfaces. Techniques developed in this project will facilitate visual data management such as next generation database in various domains including personal digital assets, entertainment, and scientific research as well as Internet search engine. Students involved in this project will be trained to enhance their knowledge base while investigating multimedia content techniques and machine learning techniques, and programming skills.

2. Mobile and Internet Multimedia Computing

Internet has been a platform for delivering a wide range of information. Particularly, multimedia information has dominated network traffic and it is anticipated that mobile Internet will be the next emerging focus since more and more portable devices get connected to Internet. Such wealthy information has enabled many research tasks to be conducted at an ever larger scale and in more convenient way, such as multimedia information retrieval, object recognition, security, multimedia forensics, and knowledge discovery. For example, a large number of diverse training samples can be easily fetched for more robust object recognition, compared with previous research on a small dataset. This project is to harvest the vast multimedia resources in Internet for multimedia information retrieval, computer vision, and multimedia data mining at Internet scale, to investigate secure multimedia information delivery in Internet, and to innovate more multimedia applications for Internet users. Students will enrich their knowledge on Internet, information retrieval, multimedia data processing, machine learning techniques, and data mining techniques in this project.

3. Multimedia Computing for Social Science

Nowadays, more and more user interactions can be analyzed through the way they share and consume multimedia information. For example, images and videos uploaded in social networks indicate where the users have been and their friends could interact with them through posts, which provides a unique and large amount of information on their social trials. In addition, more and more advanced portable devices such as smart phones enable more multi-modal information acquisition through various sensors such as location and cameras. Therefore, this cross-disciplinary project at a never better time is to empower the research on social science with advanced multimedia computing techniques, to facilitate innovation on multimedia computing through new discoveries on social science, and to invent novel multimedia enabled applications for developing better social communities. This multi-disciplinary project will assist students in developing their cross-disciplinary knowledge on social science, multimedia content analysis, and data mining.

4. Digital TV News Content Management

TV news is still indispensable for majority of people to acquire information, though the distribution of TV news has been diverse due to the rise of advanced Web technologies. There has not been much advance in assisting users in consuming such information, though there have been many research outcomes on analyzing TV news contents such as commercial detection, story detection and classification. This project is to investigate novel approaches so that users can play a more active and informed role in consuming TV news and obtaining insights, and to derive new knowledge from a large news repository. Its research topics will include intelligent information retrieval, topic discovery, threading and tracking, and knowledge discovery. Students will develop strong skills in multimedia content analysis, machine learning, and data mining.

5. Plant Image Management

Obtaining sufficient knowledge of plants is crucial for the sustainable development for our earth, such as environment protection. The visual appearance of plants plays an important role in managing plant data and experienced botanists can identify plant species through visual hints of leaves such as shape contour and vein texture. This project is to improve plant image management through innovative visual information processing, modeling, and machine learning techniques so as to accumulate and even explore knowledge for intelligent decision making. Students will gain comprehensive knowledge of image processing, machine learning, and computer graphics as well as interesting botanical knowledge.

6. Human Motion Analysis, Modeling, Animation, and Synthesis

People are the focus in most activities; hence investigating human motion has been driven by a wide range of applications such as visual surveillance, 3D animation, advanced Human Computer Interaction, sports, and medical diagnosis and treatment. This project is to address a number of challenge issues of this area in realistic scenarios, including human tracking, motion detection, recognition, modeling, animation, and synthesis. Students will gain comprehensive knowledge in computer vision (e.g. object segmentation and tracking, and action/event detection and recognition), 3D modeling, computer graphics, and machine learning.

Supervisors: Dr Zhiyong Wang and Prof David Feng

1. Mobile and Internet Multimedia Computing

Internet has been a platform for delivering a wide range of information. Particularly, multimedia information has dominated network traffic and it is anticipated that mobile Internet will be the next emerging focus since more and more portable devices get connected to Internet. Such wealthy information has enabled many research tasks to be conducted at an ever larger scale and in more convenient way, such as multimedia information retrieval, object recognition, security, multimedia forensics, and knowledge discovery. For example, a large number of diverse training samples can be easily fetched for more robust object recognition, compared with previous research on a small dataset. This project is to harvest the vast multimedia resources in Internet for multimedia information retrieval, computer vision, and multimedia data mining at Internet scale, to investigate secure multimedia information delivery in Internet, and to innovate more multimedia applications for Internet users. Students will enrich their knowledge on Internet, information retrieval, multimedia data processing, machine learning techniques, and data mining techniques in this project.

2. Plant Image Management

Obtaining sufficient knowledge of plants is crucial for the sustainable development for our earth, such as environment protection. The visual appearance of plants plays an important role in managing plant data and experienced botanists can identify plant species through visual hints of leaves such as shape contour and vein texture. This project is to improve plant image management through innovative visual information processing, modeling, and machine learning techniques so as to accumulate and even explore knowledge for intelligent decision making. Students will gain comprehensive knowledge of image processing, machine learning, and computer graphics as well as interesting botanical knowledge.

3. Video Summarization

It is difficult for us to quickly understand video contents, though it is trivial to glance through a textual document such as articles and web pages. Video summarization is to generate condensed yet informative version of given video footages so that video information can be quickly consumed and has a wide range of applications such as identifying desired contents from the videos returned by search engines. This project is to develop a system to create a summary for a given video footage. Students participating in this project will enhance their knowledge in video content analysis as well as programming skills.

Publications

More are available at Google Scholar

2010

46. Z. Wang and D. Feng, "Discovering Semantics from Visual Information," Machine Learning Techniques for Adaptive Multimedia Retrieval: Technologies Applications and Perspectives, Chia-Hung Wei (Editor), IGI Global, 2010. [Pre-Print] [Online]
45. S. Mei, M. He, Z. Wang, and D. Feng, "Spatial Purity based Endmember Extraction for Spectral Mixture Analysis," IEEE Trans. on Geoscience and Remote Sensing, Vol. 48, No. 9, pp. 3434-3445, September, 2010.
44. S. Mei, M. He, Z. Wang, and D. Feng, "Mixture Analysis by Multichannel Hopfield Neural Network," IEEE Geoscience and Remote Sensing Letters, Vol. 7, No. 3, pp. 455-459, July 2010.
43. H.-K. Cheung, W. C. Siu, D. Feng and Z. Wang, "An Efficient Retinex-Like Brightness Normalization Method for Coding Camera Flashes and Strong Brightness Variation in Videos," Signal Processing: Image Communication, Vol. 25, No. 3, pp. 143-162, March 2010
42. K. Yu, Z. Wang, L. Zhuo, and D. Feng, "Harvesting Web Images for Realistic Facial Expression Recognition," International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, Australia, December, 2010.
41. Q. Wu, Z. Wang, F. Deng, and D. Feng, "Realistic Human Action Recognition with Audio Context," International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, Australia, December, 2010.
40. Y. Qiu, G. Guan, Z. Wang, and D. Feng, "Improving News Video Annotation with Semantic Context," International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, Australia, December, 2010.
39. S. Lu, Z. Wang, Me. Wang, M. Ott, and D. Feng, "Adaptive Reference Frame Selection for Near-Duplicate Video Shot Detection," IEEE International Conference on Image Processing (ICIP), Hong Kong, September, 2010.
38. P. Dong, Z. Wang, L. Zhuo, and D. Feng, "Video Summarization with Visual and Semantic Features," Pacific-Rim Conference on Multimedia (PCM), Shanghai, China, September, 2010.
37. J. Niu, Z. Wang, and D. Feng, "Two-step Similarity Matching for Content-based Video Retrieval in P2P Networks," IEEE International Workshop on Networking Issues in Multimedia Entertainment (NIME) in conjunction with IEEE International Conference on Multimedia & Expo (ICME), Singapore, July 2010.
36. L. Zhang, Z. Wang, and D. Feng, "Efficient High-dimensional Retrieval in Structured P2P Networks," International Workshop on Advances in Music Information Research (AdMIRe) in conjunction with IEEE International Conference on Multimedia & Expo (ICME), Singapore, July 2010.
35. G. Zhou, Z. Wang, J. Wang, and D. Feng, "Spatial context for visual vocabulary construction," International Conference on Image Analysis and Signal Processing (IASP), pp.176-181, Xiamen, China, April, 2010.

2009

34. F.-Z. Pavel, Z. Wang, D. Feng, "Reliable Object Recognition Using SIFT Features," Proc. of the IEEE International Workshop on Multimedia Signal Processing (MMSP 2009), Rio de Janeiro, Brazil, 5-7 October 2009.
33. L. Zhang, Z. Wang, D. Feng, "Two-Level Indexing for High-Dimensional Range Queries in Peer-to-Peer Networks," Proc. of the IEEE International Workshop on Multimedia Signal Processing (MMSP 2009), Rio de Janeiro, Brazil, 5-7 October 2009.
32. G. Guan, Z. Wang, Q. Tian, D. Feng, "Improved Concept Similarity Measuring in Visual Domain," Proc. of the IEEE International Workshop on Multimedia Signal Processing (MMSP 2009), Rio de Janeiro, Brazil, 5-7 October 2009.
31. Z. Wang, H. Yi, J. Wang, D. Feng, "Hierarchical Gaussian Mixture Model for Image Annotation via PLSA," Proceedings of the International Conference on Image and Graphics (ICIG'09), XiĄŻan, China, 21-23 September 2009.
30. S. Mei, M. He, Z. Wang, and D. Feng, "Spectral-spatial Endmember Extraction by Singular Value Decomposition for AVIRIS data," Proc of the IEEE Conference on Industrial Electronics and Applications (ICIEA 2009), XiĄŻan, China, May 2009.

2008

29. Z. Wang, G. Guan, J. Wang, and D. Feng, "Measuring Semantic Similarity between Concepts in Visual Domain," Proc. of the IEEE International Workshop on Multimedia Signal Processing (MMSP 2008), Cairns, Australia, October 2008.
28. Z. Wang, W.-C. Siu, and D. Feng, "Image Annotation with Parametric Mixture Model based Multi-Class Multi-Labeling," Proc. of the IEEE International Workshop on Multimedia Signal Processing (MMSP 2008), Cairns, Australia, October 2008.
27. H.-K. Cheung, W.-C. Siu, Dagan Feng, and Zhiyong Wang, "Windowing Technique for the DCT Based Retinex Algorithm to Handle Videos with Brightness Variations Coded Using the H.264," Proc. of the IEEE International Conference on Image Processing (ICIP 2008), San Diego, USA, October 2008.
26. H. K. Cheung, W. C. Siu, D. Feng and Z. Wang, "Constrained One-bit Transform for Retinex based Motion Estimation for Sequences with Brightness Variations," Proceedings, IEEE International Conference on Neural Networks and Signal Processing (ICNNSP 2008), Zhenjiang, China, June 2008.
25. H. K. Cheung, W. C. Siu, D. Feng, and Z. Wang, "Retinex Based Motion Estimation for Sequences with Brightness Variations and Its Application to H.264," Proc. of the IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2008), Las Vegas, USA, March 2008.

2007 and older

24. J. Kim, Z. Wang, W. Cai, and D. Feng, "Multimedia for Future Health ¨C Smart Medical Home," Biomedical Information Technology, D. Feng (Editor.), Elsevier, 2007.
23. L. Zhuo, X. Gao, Z. Wang, D. Feng, and L. Shen, "A Novel Rate-quality Model based H.265 AVC Frame Layer Rate Control Method," Proc. of the Sixth International Conference on Information, Communication and Signal Processing (ICICS 2007), Singapore, December 2007.
22. B. Xie, Z. Wang, and J. Wang, "Shape Classification Using Hidden Markov Model and Structural Feature," Proc. of the SPIE International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR 2007), Wuhan, China, November 2007.
21. Z. Wang, K. Lam, L. Zhuo, and D. Feng, "Concept Constrained Image Region Annotation," Proc. of the IEEE International Workshop on Multimedia Signal Processing (MMSP 2007), Chania, Greece, October 2007.
20. Z. Wang and D. Feng, "Utilizing Structural Context for Region Classification," Intelligent Information Processing III, Zhongzhi Shi, K. Shimobara, and D. Feng (Eds.), Springer, pp. 357-366, 2006.
19. Z. Wang, D. Feng, Z. Chi, and T. Xia, "Annotating Image Regions Using Spatial Context," Proc. of the IEEE International Symposium on Multimedia (ISM 2006), San Diego, CA, USA, December 2006.
18. Z. Wang, D. Feng, and Z. Chi, "Comparison of Image Partition Methods for Adaptive Image Categorization Based on Structural Image Representation," Proc. of the 8th International Conference on Control, Automation, Robotics and Vision (ICARCV 2004), pp. 676-680, Kunming, China, 6-9 December 2004.
17. Z. Wang, Z. Chi, and D. Feng, "Leaf Image Retrieval Using Combined Shape Feature Sets with Fuzzy Integral," Chinese Journal of Electronics, Vol.12, No.4, pp.572-578, Oct. 2003.
16. Z. Wang, Z. Chi, D. Feng, and A.C. Tsoi, "Content-based image retrieval with relevance feedback using adaptive processing of tree-structure image representation," International Journal of Image and Graphics, Vol. 3, No. 1, pp. 119-143, 2003.
15. S.Y. Cho, Z. Chi, Z. Wang, and W.C. Siu, "An Efficient Learning Algorithm for Adaptive Processing of Data Structure," Neural Processing Letters, Vol. 17, No. 2, pp. 175-190, Apr. 2003.
14. Z. Wang, Z. Chi, and D. Feng, "Shape Based Leaf Image Retrieval," IEE Proceedings - Vision, Image and Signal Processing, Vol. 150, No. 1, pp. 34-43, Feb. 2003. [Cited by 64, Google Scholar 2010]
13. Z. Wang, D. Feng, and Z. Chi, "Region-based Binary Tree Representation for Image Classification," Proc. of the IEEE International Conference on Neural Network and Signal Processing 2003 (NNSP2003), Vol. I, pp.232-235, Dec. 12-15, 2003, Nanjing, China.
12. A. Hong, Z. Chi, G. Chen, and Z. Wang, "Region-of-interest based flower images retrieval," Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'03), Vol. III, pp.589-592, 2003.
11. Z. Wang, Z. Chi, and D. Feng, "Structural Representation and BPTS Learning for Shape Classification," Proc. of the 9th International Conference on Neural Information Processing (ICONIP2002), pp. 134-148, Nov. 18-22, 2002, Singapore.
10. S.Y. Cho, Z. Wang, Z. Chi, and W.C. Siu, "Robust Learning in Adaptive Processing of Data Structures for Tree Representation based Images Classification," Proc. of the International Conference on Pattern Recognition (ICPR 2002), Vol. II, pp. 108-111, August 11-15, 2002, Quebec City, Canada.
9. Z. Wang, Z. Chi, and D. Feng, "Fuzzy Integral for Leaf Image Retrieval," Proc. of the 2002 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE2002), pp. 372-377, May 12-17, 2002, Honolulu, Hawaii, USA.
8. Z. Wang, M. Hagenbuchner, A.C. Tsoi, S.Y. Cho, and Z. Chi, "Image Classification with Structured Self-Organization Map," Proc. of the 2002 International Joint Conference on Neural Networks (IJCNN2002), pp.1918-1923, May 12-17, 2002, Honolulu, Hawaii, USA.
7. Z. Wang, Z. Chi, D. Feng, and S. Y. Cho, "Adaptive Processing of Tree-Structure Image Representation," Lecture Notes in Computer Science 2195: Advances in Multimedia Information Processing, Heung-Yeung Shum, Mark Liao and Shih-Fu Chang (Eds.), Springer-Verlag, pp. 989-995, 2001.
6. Z. Wang, Z. Chi, D. Feng, and Q. Wang, "Leaf Image Retrieval with Shape Features," Lecture Notes in Computer Science 1929: Advances in Visual Information Systems, R. Laurini (Ed.), Springer-Verlag, pp. 477-487, 2000.
5. Z. Wang, Z. Chi and Y. Yu, "Fractal Coding for Image Retrieval," Acta Electronica Sinica, Vol. 28, No. 6, pp. 19-23, June 2000, China. (in Chinese)
4. Z. Wang, Z. Chi, and D. Feng, "Content-based Image Retrieval Using Block-Constrained Fractal Coding and Nona-Tree Decomposition," IEE Proceedings - Vision, Image and Signal Processing, Vol. 147, No. 1, pp. 9-15, February 2000, UK.
3. Z. Wang, Z. Chi, and D. Feng, "Leaf Image Retrieval Using a Two-Step Approach with Shape Features," Proc. of 2000 IEEE Pacific-Rim Conference on Multimedia (PCM2000), pp. 380-383, December 12-15, 2000, Sydney, Australia.
2. Z. Wang, Z. Chi, D. Deng, and Y. Yu, "Block-Constrained Fractal Coding Scheme for Image Retrieval," Lecture Notes in Computer Science 1614: Visual Information and Information Systems, D.P. Huijsmans and A.W.M. Smeulders (Eds.), Springer-Verlag Berlin Heidelberg, pp. 673-680, 1999.
1. Z. Wang, D. Deng, and Y. Yu, "Fractal Technique for Color Texture Segmentation," Journal of South China University of Technology (Natural Science), Vol. 26, No. 10, pp. 64-70, 1998, China. (in Chinese)

Last Update: Dec 2013