In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation ...
Abstract. We propose a novel method to detect human poses in videos by concurrently optimizing body part matching and object segmentation. With a single exemplar image, the propose...
By mapping a set of input images to points in a lowdimensional manifold or subspace, it is possible to efficiently account for a small number of degrees of freedom. For example, i...
Solids of revolution (vases, bottles, bells, . . .), shortly SORs, are very common objects in man-made environments. We present a complete framework for 3D database population from...
Carlo Colombo, Dario Comanducci, Alberto Del Bimbo...
We present a new approach to appearance-based object recognition, which captures the relationships between multiple model views and exploits them to improve recognition performanc...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...