Event Location: NSH 1305
Bio: Iasonas Kokkinos obtained the Diploma of Engineering in 2001 and the Ph.D. Degree in 2006, both from the School of Electrical and Computer Engineering of the National Technical University of Athens in Greece. In 2006 he joined the Center for Image and Vision Sciences in the University of California at Los Angeles as a postdoctoral scholar. As of 2008 he is an Assistant Professor at the Department of Applied Mathematics of Ecole Centrale Paris and is also affiliated with the Galen group of INRIA-Saclay in Paris.

His research interests are in the broader areas of computer vision, signal processing and machine learning, while he has worked on nonlinear speech processing, biologically motivated vision, texture analysis and image segmentation. His currently research activity is focused on efficient algorithms for object detection, shape-based object recognition and learning-based approaches to feature detection.

He has been awarded a young researcher grant by the French National Research Agency, and serves regularly as a reviewer for all major computer vision conferences and journals; he has served as an area chair for CVPR 2012, co-organized POCV 2012 and is an associate editor for the Image and Vision Computing Journal.

Abstract: Accommodating shape variability is crucial for robust object category detection, but typically comes at the cost of computational complexity.

In the first part of this talk we will see how bounding-based techniques, such as Branch-and-Bound and Cascaded Detection can be used for detection with Deformable Part Models (DPMs). Instead of evaluating the classifier score exhaustively over all image locations and scales, such techniques use bounding to focus on promising image locations. We evaluate our approach using the DPM models of Felzenszwalb and coworkers, and obtain exactly the same results but cut down computation time by an
order of magnitude.

In the second part I will present one method to learn and integrate contours in a hierarchical object representation for object recognition. I will overview Active Appearance Model (AAM)-based algorithms for acquiring the shape models through groupwise registration, and coarse-to-fine inference/A* algorithms that have been developed around hierarchical, contour-based object representations.