Modeling Local Descriptors with Multivariate Gaussians for Object and Scene Recognition

Abstract: Common techniques represent images by quantizing local descriptors and summarizing their distribution in a histogram. In this paper we propose to employ a parametric description and compare its capabilities to histogram based approaches. We use the multivariate Gaussian distribution, applied over the SIFT descriptors, extracted with dense sampling on a spatial pyramid. Every distribution is converted to a high-dimensional descriptor, by concatenating the mean vector and the projection of the covariance matrix on the Euclidean space tangent to the Riemannian manifold. Experiments on Caltech-101 and ImageCLEF2011 are performed using the Stochastic Gradient Descent solver, which allows to deal with large scale datasets and high dimensional feature spaces.

Citation:

Serra, Giuseppe; Grana, Costantino; Manfredi, Marco; Cucchiara, Rita "Modeling Local Descriptors with Multivariate Gaussians for Object and Scene Recognition" Proceedings of the 21th International Conference on Multimedia (ACM Multimedia 2013), Barcelona, Catalunya, Spain, pp. 709 -712 , Oct 21-25, 2013 DOI: 10.1145/2502081.2502185

 not available

Paper download:

• Author version:
• DOI: 10.1145/2502081.2502185