HAL - INRIA :: [inria-00548675, version 1] Vector quantizing feature space with a regular lattice

inria-00548675, version 1

Vector quantizing feature space with a regular lattice

Tinne Tuytelaars ¹, Cordelia Schmid () ^2, 3

11th IEEE International Conference on Computer Vision (ICCV '07) (2007) 1--8

Abstract: Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a data- independent approach to construct such a visual vocabulary, where the feature space is discretized using a regular lattice. Using hashing techniques, only non-empty bins are stored, and fine-grained grids become possible in spite of the high dimensionality of typical feature spaces. Based on this representation, we can explore the structure of the feature space, and obtain state-of-the-art pixelwise classification results. In the case of image classification, we introduce a class-specific feature selection step, which takes the spatial structure of SIFT-like descriptors into account. Results are reported on the Graz02 dataset.

1: Department of Electrical Engineering (ESAT)
Katholieke Universiteit Leuven
2: LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
3: Laboratoire Jean Kuntzmann (LJK)
CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Université Pierre Mendès-France - Grenoble II – Institut Polytechnique de Grenoble - Grenoble Institute of Technology

inria-00548675, version 1
http://hal.inria.fr/inria-00548675
oai:hal.inria.fr:inria-00548675
From: Team Lear <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 10:27:13
Updated on: Monday, 10 January 2011 17:16:04

See detailed view

Associated documents

PDF :

DOI: 10.1109/ICCV.2007.4408924

Full text from publisher

Export

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00548675"><analytic>
<author><persName><forename>Tinne</forename><surname>Tuytelaars</surname></persName>
<affiliation>
<orgName type="laboratory">ESAT</orgName>
<orgName type="team">Department of Electrical Engineering</orgName>
<country>BE</country>
<orgName type="institution">Katholieke Universiteit Leuven</orgName>
</affiliation>
</author>
<author><persName><forename>Cordelia</forename><surname>Schmid</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">LEAR</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">LJK</orgName>
<orgName type="team">Laboratoire Jean Kuntzmann</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Université Pierre Mendès-France - Grenoble II</orgName>
<orgName type="institution">Institut Polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
</affiliation>
</author>
<title type="main" level="a">Vector quantizing feature space with a regular lattice</title></analytic><monogr><meeting>11th IEEE International Conference on Computer Vision (ICCV '07)</meeting><imprint><publisher>IEEE Computer Society</publisher><pubPlace><settlement>Rio de Janeiro</settlement><country>Brazil</country></pubPlace><biblScope type="publicationDate">2007-00-00</biblScope><biblScope type="pp">1--8</biblScope></imprint></monogr><idno type="doi">10.1109/ICCV.2007.4408924</idno><idno type="HALid">http://hal.inria.fr/inria-00548675</idno><idno type="HALFile">http://hal.inria.fr/inria-00548675/PDF/Tuytelaars_Schmid-lattice-iccv07.pdf</idno></biblStruct>
</listBibl>
</listBibl>