|
Subhransu Maji Correspondence address: 1350 N Lake Shore Dr., Unit 2002, Chicago, IL - 60610 E-mail: smaji@ttic.edu Phone: (+1) 773 702 2252 |
Application materials
- Research statement
- Teaching statement
- Curriculum vitae
- References
- PhD Thesis : Algorithms and Representations for Visual Recognition
Selected publications
 |
Efficient Classification for Additive Kernel SVMs Subhransu Maji, Alexander C. Berg and Jitendra Malik IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 35, No. 1, January 2013 Efficient non-linear kernel SVM evaluation for commonly used classifiers in computer vision offering orders of magnitude savings in memory and time (initial version appeared in CVPR 2008). |
 |
Part and
Attribute Discovery from Relative Annotations Subhransu Maji and Gregory Shakhnarovich Submitted to International Journal of Computer Vision Novel annotation tools and methods for `crowdsourced' part and attribute discovery (based on papers that appeared at CVPR 2013, HCOMP 2012, and ECCV 2012). |
 |
Action Recognition from a Distributed Representation of Pose and Appearance Subhransu Maji, Lubomir Bourdev and Jitendra Malik CVPR 2011, Colorado Springs, USA CVPR poster | Code & details for: Pose estimation , Action classification Models for predicting the action and 3d pose of humans from still images. |
 |
Biased Normalized Cuts Subhransu Maji, Nisheeth Vishnoi and Jitendra Malik CVPR 2011, Colorado Springs, USA Webpage | CVPR poster Linear time normalized cuts with constraints. |
 |
Detecting People Using Mutually Consistent Poselet Activations Lubomir Bourdev, Subhransu Maji, Thomas Brox and Jitendra Malik ECCV 2010, Crete, Greece Webpage | ECCV poster A top-performing person detector on the PASCAL VOC dataset. |
 |
Max-Margin Additive Classifiers for Detection Subhransu Maji and Alexander C. Berg ICCV 2009, Kyoto, Japan (Oral) Talk slides | Code Train additive classifiers an order-of-magnitude faster with no loss in accuracy. |
 |
Object Detection Using a Max-Margin Hough Transform Subhransu Maji and Jitendra Malik CVPR 2009, Miami, Florida (Oral) Talk slides Voting based methods to speed up object detection |