Abstract

It is common to use domain specific terminology – attributes – to describe the visual appearance of ob jects. In order to scale the use of these describable visual attributes to a large number of categories, espe- cially those not well studied by psychologists or linguists, it will be neces- sary to find alternative techniques for identifying attribute vocabularies and for learning to recognize attributes without hand labeled training data. We demonstrate that it is possible to accomplish both these tasks automatically by mining text and image data sampled from the Internet. The proposed approach also characterizes attributes according to their visual representation: global or local, and type: color, texture, or shape. This work focuses on discovering attributes and their visual appearance, and is as agnostic as possible about the textual description.