In dimensionality reduction approaches, the data are typically embedded in a Euclidean latent space. However for some data sets this is inappropriate. For example, in human motion...
Raquel Urtasun, David J. Fleet, Andreas Geiger, Jo...
This paper presents a component based deformable
model for generalized face alignment, in which a novel bistage
statistical framework is proposed to account for both
local and g...
The appearance of non-rigid objects detected and tracked in video streams is highly variable and therefore makes the identification of similar objects very complex. Furthermore, i...
In modelling nonstationary sources, one possible strategy is to define a latent process of strictly positive variables to model variations in second order statistics of the underly...
— The automatic extraction and analysis of visual information is becoming generalised. The first step in this processing chain is usually separating or segmenting the captured v...