Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

ICCV
2011
IEEE

favoriteEmaildiscussreport

172views Computer Vision» more ICCV 2011»

A Graph-matching Kernel for Object Categorization

12 years 4 months ago

A Graph-matching Kernel for Object Categorization

Download www.di.ens.fr

This paper addresses the problem of category-level image classiﬁcation. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reﬂect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classiﬁcation, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.

Olivier Duchenne, Armand Joulin, Jean Ponce

Real-time Traffic

Approximate Algorithm | Computer Vision | Grid Structure | ICCV 2011 | Nearby Regions |

claim paper

Related Content

» Groupsensitive multiple kernel learning for object categorization

» Learning the Kernel Combination for Object Categorization

» Object Categorization Based on Kernel Principal Component Analysis of Visual Words

» Object Categorization via Local Kernels

» Combining brain computer interfaces with vision for object categorization

» Towards optimal bagoffeatures for object categorization and semantic video retrieval

» Combining generic and classspecific codebooks for object categorization and detection

» Active Learning with Gaussian Processes for Object Categorization

» Learning Compositional Categorization Models

Post Info
More Details (n/a)

Added	11 Dec 2011
Updated	11 Dec 2011
Type	Journal
Year	2011
Where	ICCV
Authors	Olivier Duchenne, Armand Joulin, Jean Ponce

Comments (0)