—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
The problem of tracking a varying number of non-rigid objects has two major difficulties. First, the observation models and target distributions can be highly non-linear and non-Ga...
Kenji Okuma, Ali Taleghani, Nando de Freitas, Jame...
As part of an investigation of scalable development techniques for systems written in the JavaTM programming language, the Forest Project is building JP, a prototype distributed pr...
We present a method to learn models of human heads for the purpose of detection from different viewing angles. We focus on a model where objects are represented as constellations ...
We present a simple framework to model contextual
relationships between visual concepts. The new framework
combines ideas from previous object-centric methods
(which model conte...
Nikhil Rasiwasia (University Of California, San Di...