The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...
In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined valu...
Trevor Darrell, David Demirdjian, Neal Checka, Ped...
Tree-structured probabilistic models admit simple, fast inference. However, they are not well suited to phenomena such as occlusion, where multiple components of an object may dis...
Visual trackan,g cou,ld be treeted as a param,eter estim.ation. problem, of target representastionbased on observations in im,age sequ.ences. A rich,er target represen,tation, wou...
A framework for photo-realistic view-dependent image synthesis of a shiny object from a sparse set of images and a geometric model is proposed. Each image is aligned with the 3D m...