Sciweavers

CVPR
2004
IEEE
14 years 11 months ago
Asymmetrically Boosted HMM for Speech Reading
Speech reading, also known as lip reading, is aimed at extracting visual cues of lip and facial movements to aid in recognition of speech. The main hurdle for speech reading is th...
Pei Yin, Irfan A. Essa, James M. Rehg
CVPR
2004
IEEE
14 years 11 months ago
Searching the Web with Mobile Images for Location Recognition
In this paper, we describe an approach to recognizing location from mobile devices using image-based web search. We demonstrate the usefulness of common image search metrics appli...
Tom Yeh, Konrad Tollmar, Trevor Darrell
CVPR
2004
IEEE
14 years 11 months ago
Collaborative Tracking of Multiple Targets
Coalescence, meaning the tracker associates more than one trajectories to some targets while loses track for others, is a challenging problem for visual tracking of multiple targe...
Ting Yu, Ying Wu
CVPR
2004
IEEE
14 years 11 months ago
Covariance-Driven Mosaic Formation from Sparsely-Overlapping Image Sets with Application to Retinal Image Mosaicing
A new technique is presented for mosaicing sparselyoverlapping image sets, with a target application of assisting the diagnosis and treatment of retinal diseases. The geometric im...
Gehua Yang, Charles V. Stewart
CVPR
2004
IEEE
14 years 11 months ago
Perceptual Organization of Radial Symmetries
Radial symmetry is an important perceptual cue for the feature-based representation, fixation, and description of large-scale data sets. A new approach based on iterative voting a...
Qing Yang, Bahram Parvin
CVPR
2004
IEEE
14 years 11 months ago
Non-Rigid Shape and Motion Recovery: Degenerate Deformations
This paper studies the problem of 3D non-rigid shape and motion recovery from a monocular video sequence, under the degenerate deformations. The shape of a deformable object is re...
Jing Xiao, Takeo Kanade
CVPR
2004
IEEE
14 years 11 months ago
Bayesian Assembly of 3D Axially Symmetric Shapes from Fragments
We present a complete system for the purpose of automatically assembling 3D pots given 3D measurements of their fragments commonly called sherds. A Bayesian approach is formulated...
Andrew R. Willis, David B. Cooper
CVPR
2004
IEEE
14 years 11 months ago
Real-Time Combined 2D+3D Active Appearance Models
Active Appearance Models (AAMs) are generative models commonly used to model faces. Another closely related type of face models are 3D Morphable Models (3DMMs). Although AAMs are ...
Jing Xiao, Simon Baker, Iain Matthews, Takeo Kanad...
CVPR
2004
IEEE
14 years 11 months ago
High-Speed Videography Using a Dense Camera Array
We demonstrate a system for capturing multi-thousand frame-per-second (fps) video using a dense array of cheap 30fps CMOS image sensors. A benefit of using a camera array to captu...
Bennett Wilburn, Neel Joshi, Vaibhav Vaish, Marc L...