—This paper is concerned with the representation and recognition of the observed dynamics (i.e., excluding purely spatial appearance cues) of spacetime texture based on a spatiot...
Abstract--Voice conversion can be formulated as finding a mapping function which transforms the features of the source speaker to those of the target speaker. Gaussian mixture mode...
Elina Helander, Tuomas Virtanen, Jani Nurminen, Mo...
Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
In this paper we consider the problem of segmenting multiple rigid motions using multi?frame point correspondence data. The main idea of the method is to group points according to...
Roberto Lublinerman, Mario Sznaier, Octavia I. Cam...
In this paper, we formally define the problem of topic modeling with network structure (TMN). We propose a novel solution to this problem, which regularizes a statistical topic mo...