We propose a method to train a cascade of classifiers by simultaneously optimizing all its stages. The approach relies on the idea of optimizing soft cascades. In particular, inst...
In recent years there has been a lot of interest in designing principled classification algorithms over multiple cues, based on the intuitive notion that using more features shou...
Given a set of machines and a set of Web applications with dynamically changing demands, an online application placement controller decides how many instances to run for each appl...
Chunqiang Tang, Malgorzata Steinder, Mike Spreitze...
Techniques that can introduce low-dimensional feature representation with enhanced discriminatory power is of paramount importance in face recognition applications. It is well kno...
Juwei Lu, Kostas N. Plataniotis, Anastasios N. Ven...
The reality gap, that often makes controllers evolved in simulation inefficient once transferred onto the real system, remains a critical issue in Evolutionary Robotics (ER); it p...