We describe a solution to the challenging problem of estimating human body shape from a single photograph or painting. Our approach computes shape and pose parameters of a 3D huma...
Peng Guan, Alexander Weiss, Alexandru O. Balan, Mi...
This study reports results of an ethnographic action research study, exploring mobile-centric internet use. Over the course of 13 weeks, eight women, each a member of a livelihood...
In this paper, we present a Vision-Based Interface guided by the user gestures. The advantage of our system is that it is built over a motion capture system that recovers the body ...
Approximate Nearest Neighbor (ANN) methods such as Locality Sensitive Hashing, Semantic Hashing, and Spectral Hashing, provide computationally ecient procedures for nding objects...
In many computer vision tasks, scene changes hinder the generalization ability of trained classifiers. For instance, a human detector trained with one set of images is unlikely t...