University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Soft assignment of visual words as linear coordinate coding and optimisation of its reconstruction error

Koniusz, P and Mikolajczyk, K (2011) Soft assignment of visual words as linear coordinate coding and optimisation of its reconstruction error In: ICIP 2011, 2011-09-11 - 2011-09-14, Brussels, Belgium.

[img] Text
06116129.pdf - ["content_typename_UNSPECIFIED" not defined]
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (496kB)
[img] Text (licence)
SRI_deposit_agreement.pdf
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (33kB)

Abstract

Visual Word Uncertainty also referred to as Soft Assignment is a well established technique for representing images as histograms by flexible assignment of image descriptors to a visual vocabulary. Recently, an attention of the community dealing with the object category recognition has been drawn to Linear Coordinate Coding methods. In this work, we focus on Soft Assignment as it yields good results amidst competitive methods. We show that one can take two views on Soft Assignment: an approach derived from Gaussian Mixture Model or special case of Linear Coordinate Coding. The latter view helps us propose how to optimise smoothing factor of Soft Assignment in a way that minimises descriptor reconstruction error and maximises classification performance. In turns, this renders tedious cross-validation towards establishing this parameter unnecessary and yields it a handy technique. We demonstrate state-of-the-art performance of such optimised assignment on two image datasets and several types of descriptors.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Authors :
NameEmailORCID
Koniusz, PUNSPECIFIEDUNSPECIFIED
Mikolajczyk, KUNSPECIFIEDUNSPECIFIED
Date : 2011
Identification Number : 10.1109/ICIP.2011.6116129
Contributors :
ContributionNameEmailORCID
http://www.loc.gov/loc.terms/relators/PBLIEEE, UNSPECIFIEDUNSPECIFIED
Depositing User : Symplectic Elements
Date Deposited : 28 Mar 2017 13:12
Last Modified : 31 Oct 2017 16:59
URI: http://epubs.surrey.ac.uk/id/eprint/806154

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800