The ability to normalize pose based on super-category landmarks can significantly improve models of individual categories when training data are limited. Previous methods have co...
In this paper we propose a new approach to shape recognition based on the wavelet transform modulus maxima. And apply it to the problem of content-based indexing and retrieval of ...
New Zernike velocity moments have been developed to describe an object, not only by its shape , but also by its motion throughout an image sequence. These are an extended form of ...
We describe an approach to object retrieval which searches for and localizes all the occurrences of an object in a video, given a query image of the object. The object is represent...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...