New Zernike velocity moments have been developed to describe an object, not only by its shape , but also by its motion throughout an image sequence. These are an extended form of ...
Video-based human recognition at a distance remains a challenging problem for the fusion of multimodal biometrics. As compared to the approach based on match score level fusion, i...
We present a Bayesian approach to image-based visual hull reconstruction. The 3-D shape of an object of a known class is represented by sets of silhouette views simultaneously obs...
Kristen Grauman, Gregory Shakhnarovich, Trevor Dar...
Plenoptic cameras1 are able to acquire multi-view content that can be displayed on auto-stereoscopic displays. Depth maps can be generated from the set of multiple views. As it is...
We present the IBM systems submitted and evaluated within the CLEAR'06 evaluation campaign for the tasks of single person visual 3D tracking (localization) and 2D face trackin...