This paper exploits the context of natural dynamic scenes
for human action recognition in video. Human actions
are frequently constrained by the purpose and the physical
propert...
Marcin Marszalek (INRIA), Ivan Laptev (INRIA), Cor...
Detecting and segmenting moving objects in dynamic scenes is a hard but essential task in a number of applications such as surveillance. Most existing methods only give good resul...
Automatic, defect tolerant registration of transmission electron microscopy (TEM) images poses an important and challenging problem for biomedical image analysis, e.g. in computat...
An integral scheme that provides a global eigen approach to the problem of face recognition of still images has been presented in [1]. The scheme is based on the representation of...
Abstract. This paper addresses the problem of automatically segmenting bone structures in low resolution clinical MRI datasets. The novel aspect of the proposed method is the combi...