Learn More
In video surveillance, classification of visual data can be very hard, due to the scarce resolution and the noise characterizing the sen-sors' data. In this paper, we propose a novel feature, the ARray of CO-variances (ARCO), and a multi-class classification framework operating on Riemannian manifolds. ARCO is composed by a structure of covari-ance matrices(More)
In surveillance applications, head and body orientation of people is of primary importance for assessing many behavioral traits. Unfortunately, in this context people are often encoded by a few, noisy pixels so that their characterization is difficult. We face this issue, proposing a computational framework which is based on an expressive descriptor, the(More)
A reformulation of Rawnsley's Kählerian coherent states (in the framework of geometric quantization) is used in order to investigate the interplay between their local and global properties (projective embeddings) and the relationship with Klauder quantization (via path integrals and the introduction of a metric on the classical phase space). A Klauder type(More)
In this paper a rigorous construction of the S 1-equivariant Dirac operator (i.e., Dirac-Ramond operator) on the space of (mean zero) loops in R d is given and its equivariant L 2-index computed. Essential use is made of innnite direct product representations of the Canonical Anticommutation Relations algebra.
In this note we first set up an analogy between spin and vorticity of a perfect 2d-fluid flow, based on the Borel-Weil contruction of the irreducible unitary representations of SU (2), and looking at the Madelung-Bohm velocity attached to the ensuing spin wave functions. We also show that, in the framework of finite dimensional geometric quantum mechanics,(More)
  • 1