Methods for controlling the adaptation process of an on-line handwritten character recognizer are studied. The classifier is based on the -nearest neighbor rule and it is adapted...
Vuokko Vuori, Jorma Laaksonen, Erkki Oja, Jari Kan...
Image-based modeling of semi-transparent, dynamic phenomena is a challenging task. We present an optical tomography method that uses an adaptive grid for the reconstruction of a t...
Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we p...
In order to overcome several limitations of structured light 3D acquisition methods, the colors, intensities, and shapes of the projected patterns are adapted to the scene. Based ...
Thomas P. Koninckx, Pieter Peers, Philip Dutr&eacu...
Visual tracking, in essence, deals with non-stationary data streams that change over time. While most existing algorithms are able to track objects well in controlled environments,...