Significant appearance changes of objects under different orientations could cause loss of tracking, "drifting." In this paper, we present a collaborative tracking framew...
The success of the e-learning paradigm observed in recent times created a growing demand for e-learning systems in universities and other educational institutions, that itself led ...
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one t...
There are well-established methods for reducing the number of support vectors in a trained binary support vector machine, often with minimal impact on accuracy. We show how reduce...
The goal of object category discovery is to automatically identify groups of image regions which belong to some new, previously unseen category. This task is typically performed i...
Carolina Galleguillos, Brian McFee, Serge Belongie...