Name that sculpture

<p>We describe a retrieval based method for automatically determining the title and sculptor of an imaged sculpture. This is a useful problem to solve, but also quite challenging given the variety in both form and material that sculptures can take, and the similarity in both appearance and nam...

Full description

Bibliographic Details
Main Authors: Arandjelović, R, Zisserman, A
Format: Conference item
Language:English
Published: Association for Computing Machinery 2012
_version_ 1826315382046064640
author Arandjelović, R
Zisserman, A
author_facet Arandjelović, R
Zisserman, A
author_sort Arandjelović, R
collection OXFORD
description <p>We describe a retrieval based method for automatically determining the title and sculptor of an imaged sculpture. This is a useful problem to solve, but also quite challenging given the variety in both form and material that sculptures can take, and the similarity in both appearance and names that can occur.</p> <p>Our approach is to first visually match the sculpture and then to name it by harnessing the meta-data provided by Flickr users. To this end we make the following three contributions: (i) we show that using two complementary visual retrieval methods (one based on visual words, the other on boundaries) improves both retrieval and precision performance; (ii) we show that a simple voting scheme on the tf-idf weighted meta-data can correctly hypothesize a subset of the sculpture name (provided that the meta-data has first been suitably cleaned up and normalized); and (iii) we show that Google image search can be used to query expand the name sub-set, and thereby correctly determine the full name of the sculpture.</p> <p>The method is demonstrated on over 500 sculptors covering more than 2000 sculptures. We also quantitatively evaluate the system and demonstrate correct identification of the sculpture on over 60% of the queries.</p>
first_indexed 2024-12-09T03:24:57Z
format Conference item
id oxford-uuid:d37ed0ad-c957-4685-8589-1cf69e228f81
institution University of Oxford
language English
last_indexed 2024-12-09T03:24:57Z
publishDate 2012
publisher Association for Computing Machinery
record_format dspace
spelling oxford-uuid:d37ed0ad-c957-4685-8589-1cf69e228f812024-11-27T14:15:56ZName that sculptureConference itemhttp://purl.org/coar/resource_type/c_5794uuid:d37ed0ad-c957-4685-8589-1cf69e228f81EnglishSymplectic ElementsAssociation for Computing Machinery2012Arandjelović, RZisserman, A<p>We describe a retrieval based method for automatically determining the title and sculptor of an imaged sculpture. This is a useful problem to solve, but also quite challenging given the variety in both form and material that sculptures can take, and the similarity in both appearance and names that can occur.</p> <p>Our approach is to first visually match the sculpture and then to name it by harnessing the meta-data provided by Flickr users. To this end we make the following three contributions: (i) we show that using two complementary visual retrieval methods (one based on visual words, the other on boundaries) improves both retrieval and precision performance; (ii) we show that a simple voting scheme on the tf-idf weighted meta-data can correctly hypothesize a subset of the sculpture name (provided that the meta-data has first been suitably cleaned up and normalized); and (iii) we show that Google image search can be used to query expand the name sub-set, and thereby correctly determine the full name of the sculpture.</p> <p>The method is demonstrated on over 500 sculptors covering more than 2000 sculptures. We also quantitatively evaluate the system and demonstrate correct identification of the sculpture on over 60% of the queries.</p>
spellingShingle Arandjelović, R
Zisserman, A
Name that sculpture
title Name that sculpture
title_full Name that sculpture
title_fullStr Name that sculpture
title_full_unstemmed Name that sculpture
title_short Name that sculpture
title_sort name that sculpture
work_keys_str_mv AT arandjelovicr namethatsculpture
AT zissermana namethatsculpture