Sciweavers

149 search results - page 26 / 30
» POP: Patchwork of Parts Models for Object Recognition
Sort
View
ICML
2008
IEEE
14 years 7 months ago
Boosting with incomplete information
In real-world machine learning problems, it is very common that part of the input feature vector is incomplete: either not available, missing, or corrupted. In this paper, we pres...
Feng Jiao, Gholamreza Haffari, Greg Mori, Shaojun ...
ISMAR
2003
IEEE
13 years 11 months ago
Fully Automated and Stable Registration for Augmented Reality Applications
We present a fully automated approach to camera registration for Augmented Reality systems. It relies on purely passive vision techniques to solve the initialization and realtime ...
Vincent Lepetit, Luca Vacchetti, Daniel Thalmann, ...
PR
2007
96views more  PR 2007»
13 years 5 months ago
Weighted and robust learning of subspace representations
A reliable system for visual learning and recognition should enable a selective treatment of individual parts of input data and should successfully deal with noise and occlusions....
Danijel Skocaj, Ales Leonardis, Horst Bischof
SIGIR
2004
ACM
13 years 11 months ago
A search engine for historical manuscript images
Many museum and library archives are digitizing their large collections of handwritten historical manuscripts to enable public access to them. These collections are only available...
Toni M. Rath, R. Manmatha, Victor Lavrenko
SIGIR
2003
ACM
13 years 11 months ago
Automatic image annotation and retrieval using cross-media relevance models
Libraries have traditionally used manual image annotation for indexing and then later retrieving their image collections. However, manual image annotation is an expensive and labo...
Jiwoon Jeon, Victor Lavrenko, R. Manmatha