Sciweavers

1367 search results - page 59 / 274
» Learning Visual Representations using Images with Captions
Sort
View
CORIA
2007
13 years 10 months ago
Propositions pour la recherche contextuelle d'images dans des documents XML
This article focusses on images retrieval in XML documents. Images retrieval can use sementical information in addition to visual features. We propose here to explore some ideas to...
Mouna Torjmen
ICASSP
2008
IEEE
14 years 3 months ago
Contextually adaptive signal representation using conditional principal component analysis
The conventional method of generating a basis that is optimally adapted (in MSE) for representation of an ensemble of signals is Principal Component Analysis (PCA). A more ambitio...
Rosa M. Figueras i Ventura, Umesh Rajashekar, Zhou...
ICIP
2006
IEEE
14 years 10 months ago
On the Use of Metrics for Multi-Dimensional Descriptors Clustering
The Visual Thesaurus is a new query approach when no starting image is available. It is a concise representation of all similar regions in a panel of visual patches; the user arra...
Hichem Houissa, Nozha Boujemaa
ICCV
2009
IEEE
13 years 6 months ago
Learning image similarity from Flickr groups using Stochastic Intersection Kernel MAchines
Measuring image similarity is a central topic in computer vision. In this paper, we learn similarity from Flickr groups and use it to organize photos. Two images are similar if th...
Gang Wang, Derek Hoiem, David A. Forsyth
RSS
2007
152views Robotics» more  RSS 2007»
13 years 10 months ago
Dimensionality Reduction Using Automatic Supervision for Vision-Based Terrain Learning
Abstract— This paper considers the problem of learning to recognize different terrains from color imagery in a fully automatic fashion, using the robot’s mechanical sensors as ...
Anelia Angelova, Larry Matthies, Daniel M. Helmick...