Recently the "bag of words" model becomes popular in the approaches to object recognition. These approaches model an image as a collection of local patches called "...
Visual vocabulary serves as a fundamental component in many computer vision tasks, such as object recognition, visual search, and scene modeling. While state-of-the-art approaches...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...
A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining ...
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezi...
We develop a novel method for class-based feature matching across large changes in viewing conditions. The method (called MBE) is based on the property that when objects share a si...