Welcome to my homepage. I am currently a PhD student in Department of Electrical Engineering, University of Southern California. My advisor is Prof. Gerard Medioni, and my research lab is Computer Vision Lab of IRIS, Viterbi School of Engineering.
I got my BS from Dept. of Electronic Engineering, Tsinghua University, Beijing, China in 2004. From 2004 to 2005, I was in Microsoft Research Asia, as a visiting student in the Visual Computing Group. I got my MS in Dept. of EE from University of California, Riverside, 2008.
Computer Vision and Statistical Machine Learning
My current research focuses on image analysis and enhancement, especially by using Tensor Voting method to explore the image geometric structure.
- Besides, I am quite interesting in the link between practical algorithms and the theory, e.g., Riemannian Manifold, Probability measure on geometric objects lie in different manifolds
- I am also interesting on the how to apply sparse representation, sparse learning and compressive sensing into computer vision research, for both low-level and high-level tasksd.
- Sparse Related Visual Learning, Self-taught Learning and Feature Extractions:
Though there are many image decomposition methods, it is hard to get both of the basis and the features to be independent without the normal distribution assumption. Recent research shows that sparseness and other constraints will lead to part-based representations results, which is similar to the receptive fields in V1 cortex in human Brain. Sparse Coding, Sparse Bayesian Learning and Compressive Sensing have been proposed for pattern learning, feature extraction, denoising and compression during the past 10 years.
In vision, self-taught learning means studying the knowledge from free-cost images in our natural environment; it is an active area in machine learning in recent years. The significance of self-taught learning is to revisit the fact that sometimes not only the labeled target data but also the relevant unlabeled data are hard to get, while at the same time the basic patterns can be embedded in the general data although it is unlabeled and with quite different distribution.
Propose a model-based feature extraction approach, which uses micro-structure modeling to design adaptive micro-patterns. We first model the micro-structure of the image by Pair-wise Markov Random Field. Then we give the generalized definition of micro-pattern based on the model. After that, we define the fitness function and compute the fitness index to encode the image’s local fitness to micro-patterns.
Papers: ICIP08, ICCV05(AMFG), US Patents
- Riemannian Manifold Learning and Graph Spectral Analysis:
The relationship between manifold dimension reduction and sparseness representations; theoretical understanding of manifold in the information theory framework.
- Face Recognitions and Similarity Measurement:
Papers: ICIP05 and Microsoft Techfest Demo 2005
- Geometric Methods and Applications:
Papers: Electronics Letters 2008 and CISS08
D. Gong, X. Zhao, Y. Li, "Tight geometric bound for Marcum Q-function", IEE Electronic Letters, Volume 44, Feb. 28, 2008. [Zhao and Gong contributed equally to this work] [new]
D. Gong, X. Zhao, Q. Yang, "Sparse Non-Negative Pattern Learning for Image Represenation", Proc. of 15th IEEE International Conference on Image Processing (ICIP) ,San Diego, California, USA, 2008, [new]
D. Gong, Y. Li, X. Zhao, "Geometric Inversion Approach for Visual Curve Estimation", Proc. of 42nd Annual Conference on Information Sciences and Systems (CISS) (Oral), Princeton, NJ, USA, 2008.
Q. Yang, D. Gong, X. Tang, “Modeling Micro-patterns for Feature Extraction”, Proc. of 10th IEEE International Conference on Computer Vision (ICCV), workshop on AMFG (Oral), pp.2-16, LCNS, Beijing, China, 2005.
D. Gong, Q. Yang, X. Tang, J. Lu, “Extracting Micro-Structural Gabor Features for Face Recognition”, Proc. of 12nd IEEE International Conference on Image Processing (ICIP), Vol. 2, pp.924-5, Genova, Italy, 2005.
D. Gong, Z. Ma, Y. Li, W. Chen, Z. Cao, "High Order Geometric Range Free Localization in Opportunistic Cognitive Sensor Networks", Proc. of 43rd IEEE ICC, workshop on CoCoNet (Oral), Beijing, China, 2008.
D. Gong, Y. Li, "Dynamic System Analysis and Generalized Optimal Code Assignment of OVSF-CDMA Systems", Proc. of 43rd IEEE International Conference on Communications (ICC) (Oral), Beijing, China, 2008.
D. Gong, Y. Yu, J. Lu, “Dynamic Code Assignment for OVSF-CDMA System”, Proc. of 48th IEEE Global Telecommunications Conference (Globecom) (Oral), Vol. 5, pp.5, St. Louis, Missouri, US, 2005.
Qiong Yang, Dian Gong, Xiaoou Tang, “Modeling Micro-Structure for Feature Extraction”, US Patent 315262.02, 2007
During the spare time, I love watching movies and listening pop music. Especially, I was a director in TDO (TDO means trade-off, it is extremely important for team work^_^) studio, Tsinghua University. We made two student movies and one music video. One of the movie is "how do I love you", which got the best idea and best actor prizes in the first Tsinghua Digital Movie Festival, 2004.
Here is the link of this movie in youku. Actually, I just found it out by accident and I really do not know who put this online, but it is fine, enjoy it:-).