Kernelized sorting

Novi Quadrianto; Alexander J. Smola; Le Song; Tinne Tuytelaars

doi:10.1109/TPAMI.2009.184

Kernelized sorting

Novi Quadrianto^*, Alexander J. Smola, Le Song, Tinne Tuytelaars

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

45 Citations (Scopus)

Abstract

Object matching is a fundamental operation in data analysis. It typically requires the definition of a similarity measure between the classes of objects to be matched. Instead, we develop an approach which is able to perform matching by requiring a similarity measure only within each of the classes. This is achieved by maximizing the dependency between matched pairs of observations by means of the Hilbert-Schmidt Independence Criterion. This problem can be cast as one of maximizing a quadratic assignment problem with special structure and we present a simple algorithm for finding a locally optimal solution.

Original language	English
Article number	5342424
Pages (from-to)	1809-1821
Number of pages	13
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	32
Issue number	10
DOIs	https://doi.org/10.1109/TPAMI.2009.184
Publication status	Published - 2010

Access to Document

10.1109/TPAMI.2009.184

Cite this

@article{d190c795cc6143399eca50a3dcb4be75,

title = "Kernelized sorting",

abstract = "Object matching is a fundamental operation in data analysis. It typically requires the definition of a similarity measure between the classes of objects to be matched. Instead, we develop an approach which is able to perform matching by requiring a similarity measure only within each of the classes. This is achieved by maximizing the dependency between matched pairs of observations by means of the Hilbert-Schmidt Independence Criterion. This problem can be cast as one of maximizing a quadratic assignment problem with special structure and we present a simple algorithm for finding a locally optimal solution.",

keywords = "Hilbert-Schmidt Independence Criterion., Sorting, kernels, matching, object alignment",

author = "Novi Quadrianto and Smola, {Alexander J.} and Le Song and Tinne Tuytelaars",

year = "2010",

doi = "10.1109/TPAMI.2009.184",

language = "English",

volume = "32",

pages = "1809--1821",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "10",

}

TY - JOUR

T1 - Kernelized sorting

AU - Quadrianto, Novi

AU - Smola, Alexander J.

AU - Song, Le

AU - Tuytelaars, Tinne

PY - 2010

Y1 - 2010

N2 - Object matching is a fundamental operation in data analysis. It typically requires the definition of a similarity measure between the classes of objects to be matched. Instead, we develop an approach which is able to perform matching by requiring a similarity measure only within each of the classes. This is achieved by maximizing the dependency between matched pairs of observations by means of the Hilbert-Schmidt Independence Criterion. This problem can be cast as one of maximizing a quadratic assignment problem with special structure and we present a simple algorithm for finding a locally optimal solution.

AB - Object matching is a fundamental operation in data analysis. It typically requires the definition of a similarity measure between the classes of objects to be matched. Instead, we develop an approach which is able to perform matching by requiring a similarity measure only within each of the classes. This is achieved by maximizing the dependency between matched pairs of observations by means of the Hilbert-Schmidt Independence Criterion. This problem can be cast as one of maximizing a quadratic assignment problem with special structure and we present a simple algorithm for finding a locally optimal solution.

KW - Hilbert-Schmidt Independence Criterion.

KW - Sorting

KW - kernels

KW - matching

KW - object alignment

UR - http://www.scopus.com/inward/record.url?scp=77956054665&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2009.184

DO - 10.1109/TPAMI.2009.184

M3 - Article

SN - 0162-8828

VL - 32

SP - 1809

EP - 1821

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 10

M1 - 5342424

ER -

Kernelized sorting

Abstract

Access to Document

Other files and links

Fingerprint

Cite this