Classification with only one labeled example per class is a challenging problem in machine learning and pattern recognition. While there have been some attempts to address this pr...
In this paper, the problem of estimating automatically the symmetry plane of bilateral objects (having perfect or imperfect mirror symmetry) in point clouds is reexamined. Classic...
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
The preservation of digital objects is a topic of prominent importance for archives and digital libraries. This paper focuses on the problem of preserving the performability of tas...
In this paper, we address the problem of partial comparison of non-rigid objects. We introduce a new class of set-valued distances, related to the concept of Pareto optimality in e...
Alexander M. Bronstein, Michael M. Bronstein, Alfr...