Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
We propose a new method for matching two 3D point sets of identical cardinality with global similarity but local non-rigid deformations and distribution errors. This problem arises...
In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our app...
Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Sh...
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...