This paper presents a method for visual object categorization based on encoding the joint textural information in objects and the surrounding background, and requiring no segmenta...
Alireza Tavakoli Targhi, Andrzej Pronobis, Heydar ...
In this paper, a mean shift-based clustering algorithm is proposed. The mean shift is a kernel-type weighted mean procedure. Herein, we first discuss three classes of Gaussian, C...
We propose a novel classification approach for automatically detecting pulmonary embolism (PE) from computedtomography-angiography images. Unlike most existing approaches that req...
In this paper we propose an extension to the standard Markov Random Field (MRF) model in order to handle layers. Our extension, which we call a Factorial MRF (FMRF), is analogous t...
Sub-pixel motion compensation plays an important role in compression efficiency within modern video codecs such as MPEG2, MPEG4 and H.264. Sub-pixel motion compensa tion is implem...