The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
action from low level features to high level semantics. Owing to the proliferation of multimedia content in the internet, there is widespread interest in the semantic web community...
— We propose to classify the behaviors of a mobile robot thanks to topological methods as an alternative to metric ones. To do so, we adapt an analysis scheme from Physics of non...
This paper presents a method that uses the level sets of volumes to reconstruct the shapes of 3D objects from range data. The strategy is to formulate 3D reconstruction as a stati...
We present an efficient colon flattening algorithm using conformal structure, which is angle-preserving and minimizes the global distortion. Moreover, our algorithm is general w...