Abstract. Discriminative and generative methods provide two distinct approaches to machine learning classification. One advantage of generative approaches is that they naturally mo...
This article describes a method to insert virtual objects into a real video stream based on feature tracking and camera pose estimation from a set of single-camera video frames. To...
In this paper we present a novel image-based 3D surface reconstruction technique that incorporates both reflectance and polarisation features into a variational framework. Our tec...
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez,...
Growing demand for ubiquitous and pervasive computing has triggered a sharp rise in handheld device usage. At the same time, dynamic multimedia data has become accepted as core ma...