In this paper we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques cal...
Determinantal point processes (DPPs), which arise in random matrix theory and quantum physics, are natural models for subset selection problems where diversity is preferred. Among...
In this paper, a new Mixture model of Dynamic pedestrian-Agents (MDA) is proposed to learn the collective behavior patterns of pedestrians in crowded scenes. Collective behaviors ...
Online boosting methods have recently been used successfully for tracking, background subtraction etc. Conventional online boosting algorithms emphasize on interchanging new weak ...
This paper introduces PoliCultura, a project created by Politecnico di Milano for the Italian schools, which has just completed three years of deployment. Participating classes (wi...
Nicoletta Di Blas, Franca Garzotto, Paolo Paolini,...