Home People Research Publications Demos
         
News Jobs Prospective
Students
About Internal

Dashan Gao

Currently with Qualcomm,

d a s h a n @ g m a i l . c o m





Dr. Dashan Gao is currently working at Qualcommm. Before joining Qualcomm, he was a research scientist at General Electric Global Research. Dr. Gao received his Ph.D. degree in Department of Electrical and Computer Engineering , University of California, San Diego (UCSD), in 2008, and his M.S. and B.S. degrees in Department of Automation, Tsinghua University, Beijing, China, in 2002 and 1999.

Research:
 

Dr. Gao's research interests includes computer vision, statistical learning, and computational models of visual attention. His current research topics focus on statistical modeling of video signals for aerial and ground surveillance applications.

Main Projects:
 
Discriminant Hypothesis for Visual Saliency
a decision-theoretic formulation of visual saliency, its biological plausibility, and applications to computer vision.
[details]
Bottom-up Saliency and Its Biological Plausibility
biological plausibility of bottom-up saliency by combination of the discriminant hypothesis and center-surround operators.
[details]
Top-down Discriminant Saliency
learning discriminant salient features for visual recognition.
[details]
Publications:
 

Journal articles

Discriminant saliency, the detection of suspicious coincidences, and applications to visual recognition
Dashan Gao, Sunhyoung Han, and Nuno Vasconcelos,
To appear in IEEE Trans. Pattern Analysis and Machine Intelligence, 2009.

Decision-theoretic saliency: computational principles, biological plausibility, and implications for neurophysiology and psychophysics
Dashan Gao and Nuno Vasconcelos,
Neural Computation, 21, 239-271, January 2009. [pdf]

On the plausibility of the discriminant center-surround hypothesis for visual saliency
Dashan Gao, Vijay Mahadevan and Nuno Vasconcelos
Journal of Vision, 8(7):13, 1-18, 2008. [doi:10.1167/8.7.13.]

Moving Vehicle Detection for Automatic Traffic Monitoring
J. Zhou, D. Gao, and D. Zhang,
IEEE Transactions on Vehicular Technology, vol.56, no.1, pp.51-59, Jan. 2007 [pdf]

Conference papers

The discriminant center-surround hypothesis for bottom-up saliency
Dashan Gao, Vijay Mahadevan and Nuno Vasconcelos,
In Proc. Neural Information Processing Systems (NIPS),
Vancouver, Canada, 2007. [ps] [pdf]

Bottom-up saliency is a discriminant process
Dashan Gao and Nuno Vasconcelos,
In Proc. IEEE International Conference on Computer Vision (ICCV),
Rio de Janeiro, Brazil, 2007. © IEEE [ps] [pdf]

Discriminant Interest Points are Stable
Dashan Gao and Nuno Vasconcelos,
In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
p1-6, Minneapolis, June 2007. © IEEE [ps] [pdf]

Decompose Document Image Using Integer Linear Programming
Dashan Gao and Yizhou Wang,
In The 9th International Conference on Document Analysis and Recognition (ICDAR) ,
Brazil, Sep. 2007. [pdf]

Decomposing Document Image by Heuristic Search
Dashan Gao and Yizhou Wang,
In Proc. The 6th International Conference Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR07) ,
China, Aug 2007. [pdf]

Integrated learning of saliency, complex features, and objection detectors from cluttered scenes
Dashan Gao and Nuno Vasconcelos,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
San Diego, June 2005. © IEEE [ps] [pdf]
(A longer version is available [ps] [pdf])

An Experimental Comparison of Three Guiding Principles for the Detection of Salient Image Locations: Stability, Complexity, and Discrimination
Dashan Gao and Nuno Vasconcelos,
The 3rd International Workshop on Attention and Performance in Computational Vision (WAPCV),
San Diego, June 2005. © IEEE [ps] [pdf]

Discriminant Saliency for Visual Recognition from Cluttered Scenes
Dashan Gao and Nuno Vasconcelos,
Proceedings of Neural Information Processing Systems (NIPS),
Vancouver, Canada, 2004. [ps][pdf] [code].

(The following papers were published when I was in Tsinghua University.)

Robust Contour Extraction for Moving Vehicle Tracking
Zhimin Fan, Jie Zhou, Dashan Gao, and Gang Rong
Proceedings of IEEE International Conference of Image Processing (ICIP), p625-628, 2002.

Contour extraction and tracking of moving vehicles for traffic monitoring
Zhimin Fan, Jie Zhou, Dashan Gao, and Zhiheng Li
Proceedings of IEEE Intelligent Transportation Systems (ITSC), p84-87, 2002.

A Novel Algorithm of Adaptive Background Estimation
Dashan Gao and Jie Zhou
Proceedings of IEEE International Conference of Image Processing (ICIP), p395-398, 2001.

SVM-based Detection of Moving Vehicles for Automatic Traffic Monitoring
Dashan Gao, Jie Zhou, and Leping Xin
Proceedings of IEEE Conference of Intelligent Transportation Systems (ITSC), p745-749, 2001

Adaptive background estimation for real-time traffic monitoring
Dashan Gao, Jie Zhou
Proceedings of IEEE Conference of Intelligent Transportation Systems (ITSC), p330-333, 2001.

Automated Cartridge Identification for Firearm Authentication
Jie Zhou, Leping Xin, Dashan Gao, Changshui Zhang, and David Zhang
Proceedings of IEEE Conference of Computer Vision and Pattern Recognition (CVPR), p749-754, 2001.

Car License Plates Detection from Complex Scene
Dashan Gao, Jie Zhou
Proceedings of International Conference of Signal Processing (ICSP), p1409-1414, 2000.

Ph.D. Dissertation

Dashan Gao, A discriminant hypothesis for visual saliency: computational principles, biological plausibility and applications in computer vision
University of California San Diego, September 2008 [pdf]

Other Talks, Abstracts and Technical Reports:
 

On the plausibility of the discriminant center-surround hypothesis for visual saliency
Dashan Gao, Vijay Mahadevan, and Nuno Vasconcelos,
Computational and Systems Neuroscience (COSYNE) 2008,
Salt Lake City, UT, 2008. [pdf]

V1 is an optimal saliency detector
Dashan Gao and Nuno Vasconcelos,
The 2007 Computational Cognitive Neuroscience Conference (CCNC 2007),
San Diego, CA, Nov. 2007. [poster]

Decision-theoretic visual saliency and its implications for pre-attentive vision
Dashan Gao and Nuno Vasconcelos,
The 40th Annual Meeting of the Society for Mathematical Psychology (MathPsych2007),
Irvine, CA, July 2007. (Oral Presentation)

A decision-theoretic saliency, its biological plausibility and implications for pre-attentive vision
Dashan Gao and Nuno Vasconcelos,
Vision Sciences Society 7th Annual Meeting (VSS07),
Sarasota, FL, May 2007. [ps] [pdf] [poster]

Decision-theoretic saliency: computational principles, biological plausibility and implications for neurophysiology and psychophysics
Dashan Gao and Nuno Vasconcelos,
Computational and Systems Neuroscience (COSYNE) 2007,
Salt Lake City, UT, Feb. 2007. [ps] [pdf] [poster]

A Bayesian Architecture for Combining Saliency Detectors
Dashan Gao and Nuno Vasconcelos,
Technical Report SVCL-TR-2005-01,
June 2005. [ps] [pdf]

Patents:
 

System and Method for Decomposing A Digital Image
Y. Wang, D. Gao, H. Hindi, M. B. Do,
Application No. 20061855-US-NP (Palo Alto Research Center, Inc.).





© SVCL