Alex Berg ...
Computer Science Building 0401
Columbia University
1214 Amsterdam Avenue
New York, NY 10027
aberg@cs.columbia.edu
Research   |   Publications   |   Teaching   |   Links
I am a research scientist at Columbia University working with Shree Nayar and Peter Belhumeur. I completed a Ph.D. in Fall 2005, at U.C. Berkeley with Jitendra Malik, and have had the chance to work with many wonderful people.
I am interested in all aspects of computer vision and related problems in other fields. My thesis was on shape and object recognition in images using a new take on deformable templates. I also work on recognizing and synthesizing human action in video, recovering human body poses from photographs, detecting and identifying human faces in images, detecting vehicles in images, and more...


Code

INRIA Pedestrian Detector | Fast IKSVM classifiers | Additive Classifiers

Research

   Shape Matching and Object Recognition
Non-rigid alignment of shapes for object recognition.

   Geometric Blur
Averaging over geometric distortions.

   Action Recognition and Synthesis
Recognizing and synthesizing actions in video.

   Recovering poses of humans in images
Finding poses in still images using exemplar based and bottom-up approaches.

   Names and Faces
Associating names and faces in news photographs.

Publications



 

Teaching

 
   Computer Science
  • cs70   Discrete Mathematics for Computer Science Fall 2000
  • cs170 Efficient Algorithms and Intractable Problems Fall 1997, Fall 1999
  • cs174 Combinatorics and Discrete Probability Spring 1998
  • cs184 Foundations of Computer Graphics Fall 1998, Spring 1999, Spring 2000
  • cs284 (Graduate) Computer-Aided Geometric Design Fall 1999
 
   Mathematics
  • math 54 Linear Algebra Spring 1996
  • math 55 Discrete Mathematics Fall 1995



 

Links


 
  * Computer Vision Seminar
Schedule for the weekly Computer Vision Seminar.
  * Computer Vision Group
  * Old Course Notes
Notes and other materials from two undergraduate theory courses I have TA'd, available upon request.
  * CGVV'01
Workshop on the Convergence of Graphics, Vision, and Video 2001.
A great workshop in Berkeley over spring break.
  * Appearance Models Course Page
A computer vision / computer graphics course at Berkley in spring 2001
in cooperation with Pat Hanrahan and others from Stanford.