In previous work we have presented a prototype of an assistant system for the blind that can be used for self-localization and interactive object identification of static objects ...
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 ...
Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supp...
A novel method for representing 3-D objects that unifies viewer and model centered object representations is presented. A unified 3-D frequency-domain representation (called Volum...
Model Abstraction from Examples Yakov Keselman, Member, IEEE, and Sven Dickinson, Member, IEEE The recognition community has typically avoided bridging the representational gap bet...