SVCL - Hamed Masnadi-Shirazi

Home People Research Publications Demos

News Jobs Prospective
Students About Internal

Hamed Masnadi-Shirazi
Department of Electrical and Computer Engineering,
University of California, San Diego
9500 Gilman Drive, Mail code 0409
EBU 1, Room 5512
La Jolla, CA 92093-0409

[email protected]
Phone: (858) 534-4538

Copyright @ 2007 www.svcl.ucsd.edu
�� -

I am a PhD student in Statistical Visual Computing Lab, ECE department, UCSD. I received my B.S. in Electrical Eng. from Shiraz University,IRAN and University of Texas at Arlington in 2003.

Research:

My research interests are computer vision, statistical signal processing and machine learning. At present, I am working on the theory and application of Bayes consistent loss functions for classifier design. I have also worked on real time face and object detection, brain EEG surprise signal detection as well as cost sensitive learning and classification algorithms.

Journal Publications:

Cost-Sensitive Boosting
Hamed Masnadi-Shirazi and Nuno Vasconcelos
IEEE Trans. on Pattern Analysis and Machine Intelligence,
vol. 32(2), 294, March 2010 . ⓒ IEEE [ps] [pdf]

Conference Publications:

TaylorBoost: First and Second-order Boosting Algorithms with Explicit Margin Control.
Mohammad Saberian, Hamed Masnadi-Shirazi and Nuno Vasconcelos.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2011.
[pdf]
Variable margin losses for classifier design.
Hamed Masnadi-Shirazi and Nuno Vasconcelos.
Neural Information Processing Systems (NIPS), Vancouver, Canada, Dec 2010.
(acceptance rate 25%)
[pdf]
Risk minimization, probability elicitation, and cost-sensitive SVMs
Hamed Masnadi-Shirazi and Nuno Vasconcelos.
International Conference on Machine Learning (ICML), 2010.
(acceptance rate 20%)
[pdf]
On the Design of Robust Classifiers for Computer Vision.
Hamed Masnadi-Shirazi, Nuno Vasconcelos and Vijay Mahadevan.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
Oral presentation (acceptance rate 5%)
CVPR Oral presentation video
[pdf]
On the Design of Loss Functions for Classification: theory, robustness to outliers, and SavageBoost.
Hamed Masnadi-Shirazi and Nuno Vasconcelos.
Proceedings of Neural Information Processing Systems (NIPS), Vancouver, Canada, Dec 2008.
Spotlight presentation (acceptance rate 10%)
[pdf]
High Detection-rate Cascades for Real-Time Object Detection.
Hamed Masnadi-Shirazi and Nuno Vasconcelos
Proceedings of IEEE International Conference on Computer Vision (ICCV) ,
Rio de Janeiro, Brazil, 2007. IEEE, [pdf]
Asymmetric Boosting
Hamed Masnadi-Shirazi and Nuno Vasconcelos
Proceedings of International Conference on Machine Learning (ICML),
Corvallis, OR, May 2007. [pdf]

Technical Reports:

Cost-Sensitive Boosting
Hamed Masnadi-Shirazi and Nuno Vasconcelos.
Technical Report SVCL_TR_2007_04, June, 2007. [pdf]

Talks:

Invited technical talk at ID Analytics Inc. titled on the design of loss functions for classification applications, San Diego, CA, September 9, 2010.
Invited technical talk at Google titled On the design of Bayes consistent loss functions for classification, Santa Monica, CA, July 30, 2010.
(Click to see video.)
Oral presentation at IEEE Conference on Computer Vision and Pattern Recognition (CVPR) on paper titled On the Design of Robust Classifiers for Computer Vision, San Francisco, CA, June 15, 2010.
(Click to see video.)

Awards and Honors:

NSF IGERT Fellowship: Vision and Learning in Humans and Machines, UCSD, 2007-09
Outstanding Teaching Assistant Award, ECE Department, UCSD UCSD

UTA Who's Who academic achievement award, 2002-2003 UTA
UTA Dean's List. UTA
UTA All A's Honor Roll UTA
UTA Research Experiences for Undergraduates, Fall 2001\ Spring 2002. UTA
1st Prize Most Technically Advanced Robot: 2nd Iranian Robot Contest, 2001. Shiraz University

Honorable mention in the Intelligent Robot Contest 2001 in Yokohama, Japan. Shiraz University

Teaching Experience:

University of California San Diego, Teaching Assistant: 2003-2010
Statistical Learning-II, 2009
Statistical Learning-II, 2007
Digital Signal Processing-C (Image Processing, Computer Vision),
Linear Control System Theory-A,
Linear Control System Theory-B,
Active Circuit Design,
Electronic Digital Circuits,
Engineering Group Design Project.
University of Texas Arlington, 2001-2003:
IEEE Tutor and Mentor for Electrical Eng. Courses,
SOAR Tutor Math and Physics.
Shiraz University,Iran, 2001:
Circuits-II,
Physics-I.

Research Experience:

University of California San Diego
NSF-IGERT graduate student researcher. 2007-2009.
University of California San Diego Swartz Center for Computational Neuroscience. 2006-2007.

University of California San Diego and NSF-IGERT Integrative Graduate Education and Research Traineeship (IGERT) on Vision and Human Learning in Humans and Machines.
Facial Feature Detection Using AdaBoost. 2004.
University of California San Diego and Calit2
Mobile Pulse Oximetry project, 2004.
University of Texas Arlington and NSF-REU program
Simulation of electro-magnetic waves using Finite Difference Time Domain method and Perfectly Matched Layers. 2002.
Siemens Corporation-Iran Telecommunication Manufacturing Company and Shiraz University
Joint robot project, 2000-2001.

Home	People	Research	Publications	Demos

News	Jobs	Prospective Students	About	Internal

I am a PhD student in Statistical Visual Computing Lab, ECE department, UCSD. I received my B.S. in Electrical Eng. from Shiraz University,IRAN and University of Texas at Arlington in 2003.

Research:
	My research interests are computer vision, statistical signal processing and machine learning. At present, I am working on the theory and application of Bayes consistent loss functions for classifier design. I have also worked on real time face and object detection, brain EEG surprise signal detection as well as cost sensitive learning and classification algorithms.

Journal Publications:

	Cost-Sensitive Boosting Hamed Masnadi-Shirazi and Nuno Vasconcelos IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 32(2), 294, March 2010 . ⓒ IEEE [ps] [pdf]


Conference Publications:
	TaylorBoost: First and Second-order Boosting Algorithms with Explicit Margin Control. Mohammad Saberian, Hamed Masnadi-Shirazi and Nuno Vasconcelos. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2011. [pdf] Variable margin losses for classifier design. Hamed Masnadi-Shirazi and Nuno Vasconcelos. Neural Information Processing Systems (NIPS), Vancouver, Canada, Dec 2010. (acceptance rate 25%) [pdf] Risk minimization, probability elicitation, and cost-sensitive SVMs Hamed Masnadi-Shirazi and Nuno Vasconcelos. International Conference on Machine Learning (ICML), 2010. (acceptance rate 20%) [pdf] On the Design of Robust Classifiers for Computer Vision. Hamed Masnadi-Shirazi, Nuno Vasconcelos and Vijay Mahadevan. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. Oral presentation (acceptance rate 5%) CVPR Oral presentation video [pdf] On the Design of Loss Functions for Classification: theory, robustness to outliers, and SavageBoost. Hamed Masnadi-Shirazi and Nuno Vasconcelos. Proceedings of Neural Information Processing Systems (NIPS), Vancouver, Canada, Dec 2008. Spotlight presentation (acceptance rate 10%) [pdf] High Detection-rate Cascades for Real-Time Object Detection. Hamed Masnadi-Shirazi and Nuno Vasconcelos Proceedings of IEEE International Conference on Computer Vision (ICCV) , Rio de Janeiro, Brazil, 2007. IEEE, [pdf] Asymmetric Boosting Hamed Masnadi-Shirazi and Nuno Vasconcelos Proceedings of International Conference on Machine Learning (ICML), Corvallis, OR, May 2007. [pdf]

Technical Reports:
	Cost-Sensitive Boosting Hamed Masnadi-Shirazi and Nuno Vasconcelos. Technical Report SVCL_TR_2007_04, June, 2007. [pdf]

Talks:
	Invited technical talk at ID Analytics Inc. titled on the design of loss functions for classification applications, San Diego, CA, September 9, 2010. Invited technical talk at Google titled On the design of Bayes consistent loss functions for classification, Santa Monica, CA, July 30, 2010. (Click to see video.) Oral presentation at IEEE Conference on Computer Vision and Pattern Recognition (CVPR) on paper titled On the Design of Robust Classifiers for Computer Vision, San Francisco, CA, June 15, 2010. (Click to see video.)

Awards and Honors:
	NSF IGERT Fellowship: Vision and Learning in Humans and Machines, UCSD, 2007-09 Outstanding Teaching Assistant Award, ECE Department, UCSD UCSD UTA Who's Who academic achievement award, 2002-2003 UTA UTA Dean's List. UTA UTA All A's Honor Roll UTA UTA Research Experiences for Undergraduates, Fall 2001\ Spring 2002. UTA 1st Prize Most Technically Advanced Robot: 2nd Iranian Robot Contest, 2001. Shiraz University Honorable mention in the Intelligent Robot Contest 2001 in Yokohama, Japan. Shiraz University

Teaching Experience:
	University of California San Diego, Teaching Assistant: 2003-2010 Statistical Learning-II, 2009 Statistical Learning-II, 2007 Digital Signal Processing-C (Image Processing, Computer Vision), Linear Control System Theory-A, Linear Control System Theory-B, Active Circuit Design, Electronic Digital Circuits, Engineering Group Design Project. University of Texas Arlington, 2001-2003: IEEE Tutor and Mentor for Electrical Eng. Courses, SOAR Tutor Math and Physics. Shiraz University,Iran, 2001: Circuits-II, Physics-I.

Research Experience:
	University of California San Diego NSF-IGERT graduate student researcher. 2007-2009. University of California San Diego Swartz Center for Computational Neuroscience. 2006-2007. University of California San Diego and NSF-IGERT Integrative Graduate Education and Research Traineeship (IGERT) on Vision and Human Learning in Humans and Machines. Facial Feature Detection Using AdaBoost. 2004. University of California San Diego and Calit2 Mobile Pulse Oximetry project, 2004. University of Texas Arlington and NSF-REU program Simulation of electro-magnetic waves using Finite Difference Time Domain method and Perfectly Matched Layers. 2002. Siemens Corporation-Iran Telecommunication Manufacturing Company and Shiraz University Joint robot project, 2000-2001.