Sciweavers

80 search results - page 10 / 16
» Learning the Kernel Combination for Object Categorization
Sort
View
CVPR
2010
IEEE
14 years 3 months ago
Multi-Class Object Localization by Combining Local Contextual Interactions
Recent work in object localization has shown that the use of contextual cues can greatly improve accuracy over models that use appearance features alone. Although many of these mo...
Carolina Galleguillos, Brian McFee, Gert Lanckriet
NIPS
2008
13 years 9 months ago
Cascaded Classification Models: Combining Models for Holistic Scene Understanding
One of the original goals of computer vision was to fully understand a natural scene. This requires solving several sub-problems simultaneously, including object detection, region...
Geremy Heitz, Stephen Gould, Ashutosh Saxena, Daph...
TIP
2011
217views more  TIP 2011»
13 years 2 months ago
Contextual Object Localization With Multiple Kernel Nearest Neighbor
—Recently, many object localization models have shown that incorporating contextual cues can greatly improve accuracy over using appearance features alone. Therefore, many of the...
Brian McFee, Carolina Galleguillos, Gert R. G. Lan...
ICIP
2009
IEEE
13 years 5 months ago
Object tracking by bidirectional learning with feature selection
This paper proposes a new tracking algorithm which combines object and background information, via building object and background appearance models simultaneously by nonparametric...
Heng Wang, Xinwen Hou, Cheng-Lin Liu
CIVR
2007
Springer
154views Image Analysis» more  CIVR 2007»
14 years 1 months ago
Representing shape with a spatial pyramid kernel
The objective of this paper is classifying images by the object categories they contain, for example motorbikes or dolphins. There are three areas of novelty. First, we introduce ...
Anna Bosch, Andrew Zisserman, Xavier Muñoz