This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
Given several related learning tasks, we propose a nonparametric Bayesian model that captures task relatedness by assuming that the task parameters (i.e., predictors) share a late...
Groupwise shape registration of raw edge sequence is addressed. Automatically extracted edge maps are treated as noised input shape of the deformable object and their registration...
We present a system at the junction between Computer Vision and Computer Graphics, to produce a 3-D model of an object as observed in a single image, with a minimum of high-level ...
The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...