|
|
Zhigang Ma
Postdoctoral Research Fellow
School of Computer Science
Carnegie Mellon University
Email: kevinma AT cs DOT cmu DOT edu
Office: 4026 Wean Hall
|
About me:
Greeting! I'm a Postdoctoral Research Fellow in the School of Computer Science at Carnegie Mellon University. I'm working with Dr. Alexander G. Hauptmann. I received my Ph.D. degree in computer science from University of Trento, Italy
in 2013 under the supervision of Prof. Nicu Sebe.
During my Ph.D. study, I had been an intern in the School of Computer Science at Carnegie Mellon University from Sep. 2011 to Mar. 2012 and from Jun. 2013 to Nov. 2013. I had been a research assistant
in the School of Computing at National University of Singapore from Sep. 2012 to Feb. 2013, working with Prof. Shuicheng Yan.
My research interest is mainly on machine learning and its application to multimedia analysis and computer vision.
You can know more of me from my CV.
Publications:
Journal Papers:
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization.
Yi Yang, Zhigang Ma, Feiping Nie, Xiaojun Chang and Alexander G. Hauptmann.
International Journal of Computer Vision, In Press.
Harnessing Lab Knowledge for Real-world Action Recognition. [The KSA dataset]
Zhigang Ma, Yi Yang, Feiping Nie, Nicu Sebe, Shuicheng Yan and Alexander G. Hauptmann.
International Journal of Computer Vision, 109(1-2): 60-73, 2014.
Knowledge Adaptation with Partially Shared Features for Event Detection Using Few Exemplars.
Zhigang Ma, Yi Yang,
Nicu Sebe and Alexander G. Hauptmann.
IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2014.2306419, 2014.
Multitask Spectral Clustering by Exploring Intertask Correlation.
Yang Yang, Zhigang Ma, Yi Yang, Feiping Nie, and Heng Tao Shen.
IEEE Transactions on Cybernetics, 2014.
GLocal tells you more: Coupling GLocal structural for feature selection with sparsity for image and video classification.
Yan Yan, Haoquan Sheng, Gaowen Liu, Zhigang Ma, Chenqiang Gao and Nicu Sebe.
Computer Vision and Image Understanding, 124: 99-109, 2014.
How to Efficiently Handle Large-Scale Multimedia Event Detection.
Zhigang Ma, Shoou-I Yu and Alexander G. Hauptmann.
E-Letter of Multimedia Communications Technical Committee (Invited Paper) 9(3): 26-28, 2014.
E-LAMP: integration of innovative ideas for multimedia event detection.
Wei Tong, Yi Yang, Lu Jiang, Shoou-I Yu, Zhen-zhong Lan, Zhigang Ma, Waito Sze, Ehsan Younessian and Alexander G. Hauptmann.
Machine Vision and Applications, 25(1): 5-15, 2014.
Image Attribut Adaptation.
Yahong Han, Yi Yang, Zhigang Ma, Haoquan Shen, Nicu Sebe and Xiaofang Zhou.
IEEE Transactions on Multimedia, 16(4): 1115-1126, 2014.
Semi-Supervised Feature Selection via Spline Regression for Video Semantic Recognition.
Yahong Han, Yi Yang, Yan Yan, Zhigang Ma, Nicu Sebe and Xiaofang Zhou.
IEEE Transactions on Neural Networks and Learning Systems, DOI: 10.1109/TNNLS.2014.2314123, 2014.
Semi-supervised Multiple Feature Analysis for Action Recognition.
Sen Wang, Zhigang Ma, Yi Yang, Xue Li, Chaoyi Pang and Alexander G. Hauptmann.
IEEE Transactions on Multimedia, 16(2): 289-298, 2014.
Multimedia Event Detection Using A
Classifier-specific Intermediate Representation. [code] [pdf]
Zhigang Ma, Yi Yang, Nicu Sebe, Kai Zheng and Alexander G. Hauptmann.
IEEE Transactions on Multimedia, 15(7):1628-1637, 2013.
Multi-Feature Fusion via Hierarchical
Regression for Multimedia Analysis. [code][
pdf ]
Yi Yang, Jingkuan Song, Zi Huang, Zhigang Ma,
Nicu Sebe and Alexander G. Hauptmann.
IEEE Transactions on
Multimedia. 15(3):572-581, 2013.
Feature Selection for Multimedia
Analysis by Sharing Information among Multiple Tasks. [code][
pdf ]
Yi Yang, Zhigang Ma, Alexander G. Hauptmann and Nicu
Sebe.
IEEE Transactions on Multimedia.
15(3):661-669,2013
Image Classification with Manifold Learning for Out-of-sample Data.
Yahong Han, Zhongwen Xu, Zhigang Ma and Zi Huang.
Signal Processing, 93(8): 2169-2177, 2013.
Fusing Inherent and External Knowledge with Nonlinear Learning for Cross-media Retrieval.
Hong Zhang, Yun Liu and Zhigang Ma.
Neurocomputing, 119:10-16, 2013.
Discriminating Joint Feature Analysis
for Multimedia Data Understanding. [code]
Zhigang Ma, Feiping Nie, Yi Yang, Jasper
Uijlings, Nicu Sebe and Alexander G. Hauptmann.
IEEE Transactions on Multimedia, 14(6):1662-1672, 2012.
Web Image Annotation via
Subspace-Sparsity Collaborated Feature Selection. [code]
Zhigang Ma, Feiping Nie, Yi Yang, Jasper
Uijlings and Nicu Sebe.
IEEE Transactions on
Multimedia, 14(4):1021-1030, 2012.
Conference Papers:
A Convex Formulation for Spectral Shrunk Clustering.
Xiaojun Chang, Feiping Nie, Zhigang Ma, Yi Yang and Xiaofang Zhou.
AAAI Conference on Artificial Intelligence, 2015.
Multiple Features But Few Labels? A Symbiotic Solution Exemplified for Video Analysis. [pdf]
Zhigang Ma, Yi
Yang, Nicu Sebe and Alexander G. Hauptmann
Proceedings of the ACM International Conference on Multimedia (Oral), 2014.
Event Detection using Multi-Level Relevance Labels and Multiple Features.
Zhongwen Xu, Ivor W. Tsang, Yi Yang, Zhigang Ma and Alexander G. Hauptmann.
IEEE International Conference on Computer Vision, 2014
How Related Exemplars Help Complex Event Detection in
Web Videos? [code][pdf]
Yi Yang, Zhigang Ma, Zhongwen Xu,
Shuicheng Yan and Alexander G. Hauptmann.
IEEE International Conference on Computer Vision, 2013
We Are Not Equally Negative: Fine-grained Labeling for
Multimedia Event Detection.
Zhigang Ma, Yi
Yang, Zhongwen Xu, Nicu Sebe and Alexander G. Hauptmann
Proceedings of the ACM International Conference on Multimedia (Oral), pages 293-302, 2013.
GLocal Structural Feature Selection with Sparsity for Multimedia Data Understanding.
Yan Yan, Zhongwen Xu, Gaowen Liu, Zhigang Ma and Nicu Sebe
Proceedings of the ACM International Conference on Multimedia, pages 537-540, 2013.
Thinking of Images as What They Are: Compound Matrix
Regression for Image Classification.
Zhigang
Ma, Yi Yang, Feiping Nie and Nicu Sebe.
Proceedings of the International Joint Conferences on Artificial Intelligence, 2013.
Complex Event Detection via Multi-Source Video
Attributes. [pdf]
Zhigang Ma, Yi Yang, Zhongwen Xu, Nicu Sebe,
Shuicheng Yan and Alexander Hauptmann.
IEEE Conference on Computer Vision and Pattern Recognition, pages 2627-2633, 2013.
Knowledge Adaptation for Ad Hoc
Multimedia Event Detection with Few Exemplars. [ code ]
Zhigang Ma, Yi Yang, Yang Cai, Nicu Sebe and Alexander G. Hauptmann.
Proceedings of the ACM International Conference on Multimedia (Oral), pages 469-478, 2012.
Robust Cross-Media Transfer for
Visual Event Detection.
Yang Yang, Yi Yang, Zi
Huang, Jiajun Liu and Zhigang Ma.
Proceedings of the ACM International Conference on Multimedia, pages 1045-1048, 2012.
Action Recognition by Exploring Data
Distribution and Feature Correlation.
Sen
Wang, Yi Yang, Zhigang Ma, Xue Li, Chaoyi Pang and Alexander G. Hauptmann.
IEEE Conference on Computer Vision and Pattern Recognition, pages 1370-1377, 2012.
Classifier-specific Intermediate
Representation for Multimedia Tasks.
Zhigang
Ma, Yi Yang, Alexander G. Hauptmann and Nicu Sebe.
ACM
International Conference on Multimedia Retrieval, 2012.
Exploiting the Entire Feature Space
with Sparsity for Automatic Image Annotation. [code]
Zhigang Ma, Yi Yang, Feiping Nie, Jasper
Uijlings and Nicu Sebe.
Proceedings of the ACM International Conference on Multimedia (Oral), pages 283-292, 2011.
L21-Norm Regularized Discriminative
Feature Selection for Unsupervised Learning. [code]
Yi Yang, Heng Tao Shen, Zhigang Ma, Zi Huang and Xiaofang Zhou.
Proceedings of the International Joint Conferences on Artificial Intelligence, pages 1589-1594, 2011.
Awards:
SIGMM Outstanding PhD Thesis Award, 2014.
Best PhD thesis by Gruppo Italiano Ricercatori in Pattern Recognition, Italy, 2014.
Best PhD thesis in ICT, University of Trento, Italy, 2014.
ACM Multimedia Student Travel Grant, 2012.
Copyright Notice: This material is presented to ensure
timely dissemination of scholarly and technical work. Copyright and all rights
therein are retained by authors or by other copyright holders. All persons
copying this information are expected to adhere to the terms and constraints
invoked by each author's copyright. In most cases, these works may not be
reposted without the explicit permission of the copyright holder.