SVCL - Mohammad Saberian

Home	People	Research	Publications	Demos

News	Jobs	Prospective Students	About	Internal

Mohammad (Ehsan) Saberian

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: mj.saberian @ gmail . com
Phone: (858) 534-4538

I am currently working at Yahoo! Labs. I received my Ph.D. degree from ECE department at UCSD (Statistical Visual Computing Lab ) in July 2014. My research interests are in the areas of computer vision and machine learning. More details about my research are below in the projects section.

Honors:

- Facebook fellowship finalist, 2012.

- Winner of Yahoo! Key Scientific Challenge in multimedia, 2011.

- Qualcomm Innovation fellowship finalist, 2010.

- Department fellowship, University of California San Diego, 2008.

Projects:

Computer Vision:

Training Detector Cascade		Pedestrian Detection	Scaling Rapid Obj. detection	Multiclass Obj. detection
Machine Learning:

	TaylorBoost	Feature Extraction/Selection	Multiclass Boosting

Publication:

Multi-Resolution Cascades for Multiclass Object Detection
Mohammad J. Saberian and Nuno Vasconcelos
In Proc. Neural Information Processing Systems (NIPS), [pdf]

Boosting Algorithm for Learning Detector Cascade
Mohammad J. Saberian and Nuno Vasconcelos
Journal of Machine Learning Research (JMLR) [pdf]

Guess-Averse Loss Functions For Cost-Sensitive Multiclass Boosting
Mohammad Saberian, Oscar Beijbom, David Kriegman and Nuno Vasconcelos
International Conference on Machine Learning (ICML), 2014 [pdf] [supp] [code]

Learning Optimal Embedded Cascades
Mohammad J. Saberian and Nuno Vasconcelos.
IEEE Transactions on Pattern Analysis and Machine Intelligence
vol. 34(10), 2005-2018, October 2012 [ps] [pdf]

Boosting Algorithms for Simultaneous Feature Extraction and Selection
Mohammad J. Saberian and Nuno Vasconcelos .
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
Providence, RI, 2012. [ps] [pdf][code]

Multiclass Boosting: Theory and Algorithms
Mohammad J. Saberian and Nuno Vasconcelos .
In Proc. Neural Information Processing Systems (NIPS),
Granada, Spain, Dec 2011. [ps] [pdf][code]

TaylorBoost: First and Second Order Boosting Algorithms with Explicit Margin Control
Mohammad J. Saberian, Hamed Masnadi-Shirazi and Nuno Vasconcelos .
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
Colorado Springs, CO, 2011. [ps] [pdf] [code]

Boosting Classifer Cascades
Mohammad J. Saberian and Nuno Vasconcelos .
In Proc. Neural Information Processing Systems (NIPS),
Vancouver, Canada, Dec 2010. [ps] [pdf]

Last update: 06/28/2012