Object motions can be represented as a sequence of shape deformations and translations which can be interpretated as a sequence of points in N-dimensional shape space. These space...
The design of feature spaces for local image descriptors is an important research subject in computer vision due to its applicability in several problems, such as visual classifi...
Abstract—This paper presents an information-theoretic approach to sensor placement that incorporates communication capacity into an optimal formulation. A new formulation is pres...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...
This paper presents a new algorithm based on boosting for interactive object retrieval in images. Recent works propose ”online boosting” algorithms where weak classifier sets...
Alexis Lechervy, Philippe Henri Gosselin, Frederic...