Dr Chang Xu

Lecturer
School of Information Technologies

J12 - The School of Information Technologies
The University of Sydney

Telephone +61 2 8627 6015

Website School of Information Technologies

Google scholar

Biographical details

Dr Chang Xu joined as Lecturer in Machine Learning and Computer Vision at the School of Information Technologies, University of Sydney in 2017. He obtained a Bachelor of Engineering from Tianjin University, China, and a Ph.D. degree from Peking University, China. While pursing his PhD degree, Chang received fellowships from IBM and Baidu. His research interests lie in machine learning, data mining algorithms and related applications in artificial intelligence and computer vision, including multi-view learning, multi-label learning, visual search and face recognition. His research outcomes have been widely published in prestigious journals and top tier conferences.

Research interests

Nowadays, data is increasingly cheap and ubiquitous. The corpuses are too voluminous to fit on a single machine. Meanwhile, the variety of data stands out on its own, as the data often include various data types, such as video, music and text. They are heterogeneity in modality, sources and semantics. On the other hand, they are typically messy, incomplete, and unstructured. Given these challenges, the ability to handle data variety and use it to our advantage is becoming ever more important.

Dr Chang Xu's passion is to devise ways to understand how data variety works and how it can be interrogated and exploited for the broadest possible purposes.

"We humans can intelligently integrate information from their natural senses of vision, hearing, touch and so on to make the decision. This innate ability enables us to confidently interpret our current environment or situation no matter how complex it is.

"A machine can also easily collect diverse information through different sensors or extractors, e.g., colour descriptor, local binary patterns, local shape descriptor and spatial temporal context captured by multiple cameras for human activity understanding in camera network, or the word content of webpage, and the website address and name to distinguish this particular web page before your eyes now.

"How best to describe these heterogeneous data, explore their underlying properties and inner relationships, and leverage them for distinct decision needs excite me about the research.

"I identify significant challenges, provide fundamental theoretical supports, and formulate innovative algorithmic solutions to understand and manipulate data variety. One of my ultimate research aims is allowing machines to intelligently handle multiple information sources like humans.

"I warmly welcome students and peers to collaborate with me in the related research fields to make contributions to the realization of Artificial Intelligence."

Selected grants

2002

  • Intelligent Medical Image Authentication Using Digital Watermarking; Xu C; DVC Research/Research and Development Scheme: Research and Development (R&D).

2000

  • Multimedia information retrieval and protection in Biomedicine; University of Sydney/Postdoctoral Fellowship.

Selected publications

Download citations: PDF RTF Endnote

Book Chapters

  • Xu, C., Feng, D., Zhu,, Y. (2001). Copyright protection for WAV-Table synthesis audio using digital watermarking. In Shum, H-Y, Liao, M and Chang, S-F (Eds.), Advances in Multimedia Information Processing-PCM 2001: Second IEEE Pacific Rim Conference on Multimedia, Beijing, China, October 24-26, 2001 Proceedings, (pp. 772-779). Germany: Springer.

Journals

  • Li, J., Xu, C., Yang, W., Sun, C., Tao, D. (2017). Discriminative Multi-view Interactive Image Re-ranking [Forthcoming]. IEEE Transactions on Image Processing. [More Information]
  • Qiao, M., Liu, L., Yu, J., Xu, C., Tao, D. (2017). Diversified dictionaries for multi-instance learning. Pattern Recognition, 64, 407-416. [More Information]
  • Wang, Y., Xu, C., You, S., Xu, C., Tao, D. (2017). Parts for the Whole: The DCT Norm for Extreme Visual Recovery (Forthcoming). IEEE Transactions on Image Processing, 23.
  • Xu, C., Liu, T., Tao, D., Xu, C. (2016). Local Rademacher Complexity for Multi-Label Learning. IEEE Transactions on Image Processing, 25(3), 1495-1507. [More Information]
  • Li, J., Xu, C., Gong, M., Xing, J., Yang, W., Sun, C. (2016). SERVE: Soft and Equalized Residual VEctors for image retrieval. Neurocomputing, 207, 202-212. [More Information]
  • Xu, C., Tao, D., Li, Y., Xu, C. (2015). Large-margin multi-view Gaussian process. Multimedia Systems, 21, 147-157. [More Information]
  • Ding, C., Xu, C., Tao, D. (2015). Multi-Task Pose-Invariant Face Recognition. IEEE Transactions on Image Processing, 24(3), 980-993. [More Information]
  • Xu, C., Tao, D., Xu, C. (2015). Multi-View Intact Space Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(12), 2531-2544. [More Information]
  • Xu, C., Tao, D., Xu, C. (2015). Multi-View Learning with Incomplete Views. IEEE Transactions on Image Processing, 24(12), 5812-5825. [More Information]
  • Xu, C., Tao, D., Li, Y., Xu, C. (2014). Large-margin multi-view Gaussian process. Multimedia Systems, 21(2), 147-157. [More Information]
  • Xu, C., Tao, D., Xu, C. (2014). Large-Margin Multi-View Information Bottleneck. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1559-1572. [More Information]
  • Luo, Y., Tao, D., Xu, C., Xu, C., Liu, H., Wen, Y. (2013). Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification. IEEE Transactions on Neural Networks and Learning Systems, 24(5), 709-722. [More Information]
  • Xu, C., Feng, D. (2002). Robust and eficient content-based digital audio watermarking. Multimedia Systems, 8(5), 353-368. [More Information]

Conferences

  • Wang, Y., Xu, C., Xu, C., Tao, D. (2017). Beyond RPCA: Flattening Complex Noise in the Frequency Domain. 31st AAAI Conference on Artificial Intelligence (AAAI-17), USA.
  • Liu, M., Xu, C., Luo, Y., Xu, C., Wen, Y., Tao, D. (2017). Cost-Sensitive Feature Selection by Optimizing F-measures. 31st AAAI Conference on Artificial Intelligence (AAAI-17), USA.
  • Wang, Y., Xu, C., Tao, D., Xu, C. (2016). CNNpack: Packing Convolutional Neural Networks in the Frequency Domain. Neural Information Processing Systems 2016 (NIPS 2016) (30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain), Barcelona: Neural Information Processing Systems (NIPS).
  • Xu, C., Tao, D., Xu, C. (2016). Robust extreme multi-label learning. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2016), New York: Association for Computing Machinery (ACM). [More Information]
  • Xu, C., Tao, D., Xu, C. (2015). Large-margin multi-label causal feature learning. 29th AAAI Conference on Artificial Intelligence (AAAI 2015), Palo Alto, California, USA: AAAI Press.
  • Xu, C., Tao, D., Xu, C. (2015). Multi-view self-paced learning for clustering. 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires: AAAI Press.
  • Xu, C., Tao, D., Xu, C., Rui, Y. (2014). Large-margin weakly supervised dimensionality reduction. 31st International Conference on Machine Learning (ICML 2014), Beijing: International Machine Learning Society.
  • Xu, C., Tao, D., Li, Y., Xu, C. (2013). Large-margin multi-view Gaussian process for image classification. 5th International Conference on Internet Multimedia Computing and Service (ICIMCS 2013), New York: Association for Computing Machinery (ACM). [More Information]
  • Luo, Y., Tao, D., Xu, C., Li, D., Xu, C. (2013). Vector-valued multi-view semi-supervised learning for multi-label image classification. 27th AAAI Conference on Artificial Intelligence (AAAI 2013), Bellevue: AAAI Press.
  • Xu, C., Li, Y., Zhou, C., Xu, C. (2012). Learning to rerank images with enhanced spatial verification. 2012 19th IEEE International Conference on Image Processing (ICIP 2012), Piscataway: (IEEE) Institute of Electrical and Electronics Engineers. [More Information]
  • Xu, C., Lim, Y., Feng, D. (2002). Recovering Modified Watermarked Audio Based on Dynamic Time-Warping Technique. The Sixth Digital Image Computing Techniques and Applications, Australia: Australian Pattern Recognition Society.
  • Lim, Y., Xu, C., Feng, D. (2002). Web Based Image Authentication Using Invisible. The Pan-Sydney Area workshop on Visual Information Processing, Australia: Association for Computing Machinery (ACM).
  • Xu, C., Feng, D., Zhu,, Y. (2001). A Robust and Fast Watermarking Scheme for Compressed Audio. 2001 IEEE Conference on Multimedia and Expo, Australia: UNSW Australian Defence Force Academy.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Content Protection and Usage Control for Digital Music. First International Conference on WEB Delivering of Music, : Ads & Adea.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Content-Based Retrieval for Digital Audio and Music. The Fifth IASTED International COnference Internet and Multimedia Systems and Applications, : UNSW Australian Defence Force Academy.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Digital Audio Watermarking Based-on Multiple-bit Hopping and Human Auditory System. 2001 Multimedia Conference, USA: UNSW Australian Defence Force Academy.
  • Lim, Y., Xu, C., Fulton, R., Feng, D. (2001). Interactive Invisible Captioning for Medical Images Using Digital Watermarking. Image and Vision Computing New Zealand 2001, Australia: UNSW Australian Defence Force Academy.
  • Xu, C., Feng, D. (2001). Web-Based Protection and Secure Distribution for Digital Music. The Fifth IASTED International COnference Internet and Multimedia Systems and Applications, : UNSW Australian Defence Force Academy.

2017

  • Wang, Y., Xu, C., Xu, C., Tao, D. (2017). Beyond RPCA: Flattening Complex Noise in the Frequency Domain. 31st AAAI Conference on Artificial Intelligence (AAAI-17), USA.
  • Liu, M., Xu, C., Luo, Y., Xu, C., Wen, Y., Tao, D. (2017). Cost-Sensitive Feature Selection by Optimizing F-measures. 31st AAAI Conference on Artificial Intelligence (AAAI-17), USA.
  • Li, J., Xu, C., Yang, W., Sun, C., Tao, D. (2017). Discriminative Multi-view Interactive Image Re-ranking [Forthcoming]. IEEE Transactions on Image Processing. [More Information]
  • Qiao, M., Liu, L., Yu, J., Xu, C., Tao, D. (2017). Diversified dictionaries for multi-instance learning. Pattern Recognition, 64, 407-416. [More Information]
  • Wang, Y., Xu, C., You, S., Xu, C., Tao, D. (2017). Parts for the Whole: The DCT Norm for Extreme Visual Recovery (Forthcoming). IEEE Transactions on Image Processing, 23.

2016

  • Wang, Y., Xu, C., Tao, D., Xu, C. (2016). CNNpack: Packing Convolutional Neural Networks in the Frequency Domain. Neural Information Processing Systems 2016 (NIPS 2016) (30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain), Barcelona: Neural Information Processing Systems (NIPS).
  • Xu, C., Liu, T., Tao, D., Xu, C. (2016). Local Rademacher Complexity for Multi-Label Learning. IEEE Transactions on Image Processing, 25(3), 1495-1507. [More Information]
  • Xu, C., Tao, D., Xu, C. (2016). Robust extreme multi-label learning. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2016), New York: Association for Computing Machinery (ACM). [More Information]
  • Li, J., Xu, C., Gong, M., Xing, J., Yang, W., Sun, C. (2016). SERVE: Soft and Equalized Residual VEctors for image retrieval. Neurocomputing, 207, 202-212. [More Information]

2015

  • Xu, C., Tao, D., Xu, C. (2015). Large-margin multi-label causal feature learning. 29th AAAI Conference on Artificial Intelligence (AAAI 2015), Palo Alto, California, USA: AAAI Press.
  • Xu, C., Tao, D., Li, Y., Xu, C. (2015). Large-margin multi-view Gaussian process. Multimedia Systems, 21, 147-157. [More Information]
  • Ding, C., Xu, C., Tao, D. (2015). Multi-Task Pose-Invariant Face Recognition. IEEE Transactions on Image Processing, 24(3), 980-993. [More Information]
  • Xu, C., Tao, D., Xu, C. (2015). Multi-View Intact Space Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(12), 2531-2544. [More Information]
  • Xu, C., Tao, D., Xu, C. (2015). Multi-View Learning with Incomplete Views. IEEE Transactions on Image Processing, 24(12), 5812-5825. [More Information]
  • Xu, C., Tao, D., Xu, C. (2015). Multi-view self-paced learning for clustering. 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires: AAAI Press.

2014

  • Xu, C., Tao, D., Li, Y., Xu, C. (2014). Large-margin multi-view Gaussian process. Multimedia Systems, 21(2), 147-157. [More Information]
  • Xu, C., Tao, D., Xu, C. (2014). Large-Margin Multi-View Information Bottleneck. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1559-1572. [More Information]
  • Xu, C., Tao, D., Xu, C., Rui, Y. (2014). Large-margin weakly supervised dimensionality reduction. 31st International Conference on Machine Learning (ICML 2014), Beijing: International Machine Learning Society.

2013

  • Xu, C., Tao, D., Li, Y., Xu, C. (2013). Large-margin multi-view Gaussian process for image classification. 5th International Conference on Internet Multimedia Computing and Service (ICIMCS 2013), New York: Association for Computing Machinery (ACM). [More Information]
  • Luo, Y., Tao, D., Xu, C., Xu, C., Liu, H., Wen, Y. (2013). Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification. IEEE Transactions on Neural Networks and Learning Systems, 24(5), 709-722. [More Information]
  • Luo, Y., Tao, D., Xu, C., Li, D., Xu, C. (2013). Vector-valued multi-view semi-supervised learning for multi-label image classification. 27th AAAI Conference on Artificial Intelligence (AAAI 2013), Bellevue: AAAI Press.

2012

  • Xu, C., Li, Y., Zhou, C., Xu, C. (2012). Learning to rerank images with enhanced spatial verification. 2012 19th IEEE International Conference on Image Processing (ICIP 2012), Piscataway: (IEEE) Institute of Electrical and Electronics Engineers. [More Information]

2002

  • Xu, C., Lim, Y., Feng, D. (2002). Recovering Modified Watermarked Audio Based on Dynamic Time-Warping Technique. The Sixth Digital Image Computing Techniques and Applications, Australia: Australian Pattern Recognition Society.
  • Xu, C., Feng, D. (2002). Robust and eficient content-based digital audio watermarking. Multimedia Systems, 8(5), 353-368. [More Information]
  • Lim, Y., Xu, C., Feng, D. (2002). Web Based Image Authentication Using Invisible. The Pan-Sydney Area workshop on Visual Information Processing, Australia: Association for Computing Machinery (ACM).

2001

  • Xu, C., Feng, D., Zhu,, Y. (2001). A Robust and Fast Watermarking Scheme for Compressed Audio. 2001 IEEE Conference on Multimedia and Expo, Australia: UNSW Australian Defence Force Academy.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Content Protection and Usage Control for Digital Music. First International Conference on WEB Delivering of Music, : Ads & Adea.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Content-Based Retrieval for Digital Audio and Music. The Fifth IASTED International COnference Internet and Multimedia Systems and Applications, : UNSW Australian Defence Force Academy.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Copyright protection for WAV-Table synthesis audio using digital watermarking. In Shum, H-Y, Liao, M and Chang, S-F (Eds.), Advances in Multimedia Information Processing-PCM 2001: Second IEEE Pacific Rim Conference on Multimedia, Beijing, China, October 24-26, 2001 Proceedings, (pp. 772-779). Germany: Springer.
  • Xu, C., Feng, D., Zhu,, Y. (2001). Digital Audio Watermarking Based-on Multiple-bit Hopping and Human Auditory System. 2001 Multimedia Conference, USA: UNSW Australian Defence Force Academy.
  • Lim, Y., Xu, C., Fulton, R., Feng, D. (2001). Interactive Invisible Captioning for Medical Images Using Digital Watermarking. Image and Vision Computing New Zealand 2001, Australia: UNSW Australian Defence Force Academy.
  • Xu, C., Feng, D. (2001). Web-Based Protection and Secure Distribution for Digital Music. The Fifth IASTED International COnference Internet and Multimedia Systems and Applications, : UNSW Australian Defence Force Academy.

For support on your academic profile contact .