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 ...
While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle pe...
Abstract. Our aim is to develop methodology for recognition of Internet portal users on the basis of their behaviours. This is a classification task in which we have thousands val...
In this paper a new solution for the single sample problem in low resolution face recognition is proposed. The proposed solution uses an enhanced virtual pose generation method to...
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...