Karim Ali Karim Ali

EPFL IC CVLAB
BC 304 (Bâtiment BC)
Station 14
CH-1015 Lausanne
Phone: (+41) 21 693 12 82
E-mail: karim.ali=[at]=epfl.ch

Research

I am studying towards a Ph.D under the supervision of Dr. François Fleuret, Dr. David Hasler and Prof. Pascal Fua. My research interests include coding and information theory, signal processing and statistical learning. My current research focuses on object detection in images using machine learning techniques such as Boosting.

  • A Real-Time Deformable Detector
    One main challenge in object detection is that object appearance can change signifcantly depending on the pose of the object. This problem is typically delt with using a view-based approach whereby a series of detectors, each specialized to a particular viewpoint, are built. We present a framework that enables a single detector, whose constituent features deform, to achieve reliable detection. As an added benefit, our framework forgoes the need to annotate training data for pose and is applicable to a variey of machine learning methods such as Boosting and Support Vector Machines.
Cars
  • FlowBoost
    It is now possible to build robust object detectors by inputing a sufficient amount of labeled data to highly generic black-box algorithms (Boosting, SVM, Decision Trees, Neural Networks, ect.). A main drawback of these methods is that such labeled data needs to be manually collected. We propose a framework to significantly reduce the amount of labeled data to be collected by exploiting the temporal consistency occurring in a training video. Our method, FlowBoost, allows for a reduction in the number of training frames up to a factor of 60. This comes with virtually no loss in performance and in some instances, gains in performance are observed.
cells

Selected Publications

FlowBoost - Appearance Learning from Sparsely Annotated Video
K. Ali, D. Hasler and F. Fleuret
IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, 2011
A Real-Time Deformable Detector
K. Ali, F. Fleuret, David Hasler and P.Fua
Accepted,TPAMI 2011
Joint Pose Estimator and Feature Learning for Object Detection
K. Ali, F. Fleuret, David Hasler and P.Fua
IEEE International Conference on Computer Vision, Kyoto, 2009
Proper Joint Source-Channel Decoding of Entropy Coded Sources
K. Ali and F. Labeau
IEEE Vehicular Technology Conference, Dallas, 2005
Reduced Complexity Joint Source-Channel Turbo Decoding
K. Ali and F. Labeau
IEEE Canadian Workshop on Information Theory, Montreal, 2005

Bio

B. Eng, Honors Eletrical Engineering, McGill University. 1998-2002
M. Eng, Telecommunications and Signal Processing, McGill University. 2002-2005
Analyst, Business and System Integration Consulting, Accenture Ltd. 2005-2007

Links

Valid CSS