We present a new unsupervised method to learn unified probabilistic object models (POMs) which can be applied to classification, segmentation, and recognition. We formulate this a...
Yuanhao Chen, Long Zhu, Alan L. Yuille, HongJiang ...
The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...
Abstract. In this paper, we present novel image-derived, invariant features that accurately capture both the geometric and color properties of an imaged object. These features can ...
In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation ...
On the basis of a case-study, we demonstrate the usefulness of topology invariants for model-driven systems development. Considering a graph grammar semantics for a relevant fragme...