Sciweavers

ICCV
2005
IEEE
16 years 2 months ago
Identifying Individuals in Video by Combining "Generative" and Discriminative Head Models
The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...
Mark Everingham, Andrew Zisserman
107
Voted
ICCV
2005
IEEE
16 years 2 months ago
Feature Hierarchies for Object Classification
The paper describes a method for automatically extracting informative feature hierarchies for object classification, and shows the advantage of the features constructed hierarchic...
Boris Epshtein, Shimon Ullman
106
Voted
ICCV
2005
IEEE
16 years 2 months ago
Can Two Specular Pixels Calibrate Photometric Stereo?
Lambertian photometric stereo with unknown light source parameters is ambiguous. Provided that the object imaged constitutes a surface, the ambiguity is represented by the group o...
Ondrej Drbohlav, Mike J. Chantler
52
Voted
ICCV
2005
IEEE
16 years 2 months ago
Incremental Discovery of Object Parts in Video Sequences
Marc Parizeau, Patrick Hébert, Stéph...
95
Voted
ICCV
2005
IEEE
16 years 2 months ago
On Optimal Light Configurations in Photometric Stereo
This paper develops new theory for the optimal placement of photometric stereo lighting in the presence of camera noise. We show that for three lights, any triplet of orthogonal l...
Ondrej Drbohlav, Mike J. Chantler
ICCV
2005
IEEE
16 years 2 months ago
Simultaneous Facial Action Tracking and Expression Recognition Using a Particle Filter
The recognition of facial gestures and expressions in image sequences is an important and challenging problem. Most of the existing methods adopt the following paradigm. First, fa...
Fadi Dornaika, Franck Davoine
ICCV
2005
IEEE
16 years 2 months ago
A Symmetric Patch-Based Correspondence Model for Occlusion Handling
Occlusion is one of the challenging problems in stereo. In this paper, we solve the problem in a segment-based style. Both images are segmented, and we propose a novel patchbased ...
Yi Deng, Qiong Yang, Xueyin Lin, Xiaoou Tang
76
Voted
ICCV
2005
IEEE
16 years 2 months ago
Avoiding the "Streetlight Effect": Tracking by Exploring Likelihood Modes
Classic methods for Bayesian inference effectively constrain search to lie within regions of significant probability of the temporal prior. This is efficient with an accurate dyna...
David Demirdjian, Leonid Taycher, Gregory Shakhnar...
99
Voted
ICCV
2005
IEEE
16 years 2 months ago
Active Search for Real-Time Vision
In most cases when information is to be extracted from an image, there are priors available on the state of the world and therefore on the detailed measurements which will be obta...
Andrew J. Davison
87
Voted
ICCV
2005
IEEE
16 years 2 months ago
BRDF Invariant Stereo Using Light Transport Constancy
Nearly all existing methods for stereo reconstruction assume that scene reflectance is Lambertian, and make use of color constancy as a matching invariant. We introduce a new inva...
James E. Davis, Ruigang Yang, Liang Wang