This paper presents a novel method for reconstructing complex 3D objects with unknown topology using silhouettes extracted from image sequences. This method exploits the duality p...
Region based features are getting popular due to their higher descriptive power relative to other features. However, real world images exhibit changes in image segments capturing ...
There are many challenges associated with the integration of synthetic and real imagery. One particularly difficult problem is the automatic extraction of salient parameters of na...
We propose a new algorithm for learning kernels for variants of the Normalized Cuts (NCuts) objective – i.e., given a set of training examples with known partitions, how should ...
Active learning techniques have gained popularity in reducing human effort to annotate data instances for inducing a classifier. When faced with large quantities of unlabeled dat...