Boqing Gong (宫博庆)

PhD candidate Advisor: Professor Fei Sha Computer Science Department University of Southern California Email: boqinggo @ usc . edu

Research interest

Machine Learnng & Computer Vision

Code/Software

GFK_v1.zip (matlab, 310k) (NEW): geodesic flow kernel for unsupervised domain adaptation (project page)

3D object retrieval

• Demo 1 to browse results
• Demo 2 (C#) to have fun

Image processing (C++, .net)

• Seam carving (.net, 6M): content-aware image resizing, content re-targeting, and object removing based on seam carving techniques (project page)
• Image stitching (.net, 3M): automatic panoramic mosaic stitching (project page)
• Corner detection (.net, 7M): Harris and Harris-Laplacian corner detectors (project page)
• Canny (.net, 10M) edge detector (project page)

Publication

Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation. B. Gong, K. Grauman, and F. Sha.
Proceedings of the International Conference on Machine Learning (ICML), Atlanta, GA, June 2013. (Accepted) [Project] [PDF] [Supp.]

Learning Semantic Signatures for 3D Object Retrieval. B. Gong, J. Liu, X. Wang, and X. Tang.
IEEE Transactions on Multimedia (TMM) , 2013. (Accepted) [PDF] [Demo-1] [Demo-2]

Geodesic Flow Kernel for Unsupervised Domain Adaptation. B. Gong, Y. Shi, F. Sha, and K. Grauman.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, June 2012. (Oral) [Project] [PDF] [Supp.] [Slides] [Code&Data]

3D Object Retrieval with Semantic Attributes. B. Gong, J. Liu, X. Wang, and X. Tang.
Proceedings of the 19th ACM international conference on Multimedia (ACM MM), Scottsdale, Arizona, USA, 2011. [PDF] [Demo-1] [Demo-2]

Boosting 3D Object Retrieval by Object Flexibility. B. Gong, C. Xu, J. Liu, and X. Tang.
Proceedings of the 17th ACM international conference on Multimedia (ACM MM), Beijing, China, 2009. [PDF]

Automatic Expression Recognition on a Single 3D Face by Exploring Shape Deformation. B. Gong, Y. Wang, J. Liu, and X. Tang.
Proceedings of the 17th ACM international conference on Multimedia (ACM MM), Beijing, China, 2009. [PDF]

Overcoming Dataset Bias: An Unsupervised Domain Adaptation Approach. B. Gong, F. Sha, and K. Grauman.
Big Data Meets Computer Vision: first international workshop on Large Scale Visual Recognition and Retrieval (BigVision) at NIPS, Lake Tahoe, NV, Dec. 2012. (Oral) [Project] [PDF] [Slides]

M.Phil. Thesis: 3D Object Retrieval and Recognition. [PDF]

Selected project

Here are some past projects, including code, documentation, and demos.

	Unsupervised Domain Adaptation Proposed a geodesic flow kernel and a measure of rank of domains (CVPR 2012), as well as a landmark-based approach (ICML 2013) : Project Page
	3D Object Retrieval Proposed two semantic signatures (TMM 2013), a user-friendly interface (ACM MM 2011), and a low-level descriptor for 3D object retrieval (ACM 2009): Demo 1 Demo 2
	Seam Carving for Content-Aware Image Resizing Implimented Avidan and Shamir's SIGGRAPH2007 paper: Seam carving for content-aware image resizing. The implimentations details, code, as well as the results can be found at: Project Page Code

Automatic Panoramic Mosaic Stitching   Project Page Code

Harris Corner & Harris-Laplacian Detectors and A 2D Fourier descriptor   Project Page Code

Canny Edge Detection   Project Page Code

Education

University of Southern California
PhD student, Computer Science department (Aug 2011--Present)

The Chinese University of Hong Kong
MPhil student, Information Engineering department (Aug 2008--Jun 2010)
Thesis: 3D Object Retrieval and Recognition [PDF]

University of Science and Technology of China
B.E., Electronic Engineering and Information Science department (Sep 2004--Jul 2008)

Selected Award

Viterbi School of Engineering Doctoral Fellowship, USC, 2011--now
Postgraduate Studentship, CUHK, 2008-2010
Outstanding Student Scholarship (Grade 1), USTC, 2005

Professional activity

Reviewer of: The Visual Computer, Advances in Multimedia
Talk at: CVPR 2012, BigVision 2012