Although many algorithms have been developed to harvest lexical resources, few organize the mined terms into taxonomies. We propose (1) a semi-supervised algorithm that uses a roo...
The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. However, these annotations may be imperfect, in the sense t...
While several hierarchical classification methods have been applied to web content, such techniques invariably rely on a pre-defined taxonomy of documents. We propose a new techni...
In order for recognition systems to scale to a larger number of object categories building visual class taxonomies is important to achieve running times logarithmic in the number o...
In this paper, we propose a method for modeling concepts in full computation-tree logic with sequence modal operators. An extended full computation-tree logic, CTLS∗ , is introdu...