The primary focus of this project is to design and implement a parallel framework for an unstructured mesh generator based on the advancing front method (AFM). In particular, we t...
This paper presents a probabilistic part-based approach for texture and object recognition. Textures are represented using a part dictionary found by quantizing the appearance of ...
We propose a feature selection method that constructs each new feature by analysis of tight error clusters. This is a greedy, time-efficient forward selection algorithm that itera...
This paper describes characteristics of information and service design by exploring the needs and motivations of tourists. Tourists are expected to be important and demanding user...
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a...
Raquel Urtasun, David J. Fleet, Aaron Hertzmann, P...