This paper presents a systematic approach to acquiring model appearance information online for monocular modelbased tracking. The acquired information is used to drive a set of co...
This paper brings a novel method for three-dimensional reconstruction of surfaces that takes advantage of the symmetry resulting from alternating the positions of a camera and a l...
Non-negative matrix factorization (NMF) is an excellent tool for unsupervised parts-based learning, but proves to be ineffective when parts of a whole follow a specific pattern. ...
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
Kernel methods provide an efficient mechanism to derive nonlinear algorithms. In classification problems as well as in feature extraction, kernel-based approaches map the original...