Abstract. We present a novel approach for human gait recognition that inherently combines appearance and motion. Dynamic texture descriptors, Local Binary Patterns from Three Ortho...
Vili Kellokumpu, Guoying Zhao, Stan Z. Li, Matti P...
In this paper, we propose an algorithm to estimate 2D shapes and positions of obstacles such as buildings using GPS and wireless communication history of mobile nodes. Our algorith...
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
Abstract. We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment ...
Abstract. Diffusion magnetic resonance imaging has led to active research in the analysis of anatomical connectivity in the brain. Many approaches have been proposed to model the ...