Search
Now showing items 1-10 of 14
Pyramid Match Kernels: Discriminative Classification with Sets of Image Features
(2005-03-17)
Discriminative learning is challenging when examples are setsof local image features, and the sets vary in cardinality and lackany sort of meaningful ordering. Kernel-based classificationmethods can learn complex decision ...
Virtual Visual Hulls: Example-Based 3D Shape Estimation from a Single Silhouette
(2004-01-28)
Recovering a volumetric model of a person, car, or other object of interest from a single snapshot would be useful for many computer graphics applications. 3D model estimation in general is hard, and currently requires ...
Virtual Visual Hulls: Example-Based 3D Shape Estimation from a Single Silhouette
(2004-01-28)
Recovering a volumetric model of a person, car, or other objectof interest from a single snapshot would be useful for many computergraphics applications. 3D model estimation in general is hard, andcurrently requires active ...
Light Field Morphable Models
(2003-04-18)
Statistical shape and texture appearance models are powerful image representations, but previously had been restricted to 2D or simple 3D shapes. In this paper we present a novel 3D morphable model based on image-based ...
Activity Zones for Context-Aware Computing
(2003-06-10)
Location is a primary cue in many context-aware computing systems, and is often represented as a global coordinate, room number, or Euclidean distance various landmarks. A user?s concept of location, however, is often ...
Conditional Random People: Tracking Humans with CRFs and Grid Filters
(2005-12-01)
We describe a state-space tracking approach based on a Conditional Random Field(CRF) model, where the observation potentials are \emph{learned} from data. Wefind functions that embed both state and observation into a space ...
Fast Contour Matching Using Approximate Earth Mover's Distance
(2003-12-05)
Weighted graph matching is a good way to align a pair of shapesrepresented by a set of descriptive local features; the set ofcorrespondences produced by the minimum cost of matching features fromone shape to the features ...
Range Segmentation Using Visibility Constraints
(2001-09-01)
Visibility constraints can aid the segmentation of foreground objects observed with multiple range images. In our approach, points are defined as foreground if they can be determined to occlude some {em empty space} in the ...
Exploring Vision-Based Interfaces: How to Use Your Head in Dual Pointing Tasks
(2002-01-01)
The utility of vision-based face tracking for dual pointing tasks is evaluated. We first describe a 3-D face tracking technique based on real-time parametric motion-stereo, which is non-invasive, robust, and self-initialized. ...
Inferring 3D Structure with a Statistical Image-Based Shape Model
(2003-04-17)
We present an image-based approach to infer 3D structure parameters using a probabilistic "shape+structure'' model. The 3D shape of a class of objects may be represented by sets of contours from silhouette views ...