Psychophysical experiments show that humans are better at perceiving rotation and expansion than translation. These findings are inconsistent with standard models of motion integr...
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...
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...
We present an approach to attention in active computer vision. The notion of attention plays an important role in biological vision. In recent years, and especially with the emergi...
We present a Bayesian method for mixture model training that simultaneously treats the feature selection and the model selection problem. The method is based on the integration of ...
Constantinos Constantinopoulos, Michalis K. Titsia...