<div class="csl-bib-body">
<div class="csl-entry">Zaharieva, M., Breiteneder, C., & Hudec, M. (2017). Unsupervised group feature selection for media classification. <i>INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL</i>. https://doi.org/10.1007/s13735-017-0126-y</div>
</div>
The selection of an appropriate feature set is crucial for the efficient analysis of any media collection. In general, feature selection strongly depends on the data and commonly requires expert knowledge and previous experiments in related application scenarios. Current unsupervised feature selection methods usually ignore existing relationships among components of multi-dimensional features (group features) and operate on single feature components. In most applications, features carry little semantics. Thus, it is less relevant if a feature set consists of complete features or a selection of single feature components. However, in some domains, such as content-based audio retrieval, features are designed in a way that they, as a whole, have considerable semantic meaning. The disruption of a group feature in such application scenarios impedes the interpretability of the results. In this paper, we propose an unsupervised group feature selection algorithm based on canonical correlation analysis (CCA). Experiments with different audio and video classification scenarios demonstrate the outstanding performance of the proposed approach and its robustness across different datasets.
en
dc.language
English
-
dc.language.iso
en
-
dc.publisher
Springer
-
dc.relation.ispartof
INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
Feature selection
en
dc.subject
CCA
en
dc.subject
Audio classification
en
dc.subject
Video classification
en
dc.title
Unsupervised group feature selection for media classification
en
dc.type
Article
en
dc.type
Artikel
de
dc.rights.license
Creative Commons Namensnennung 4.0 International
de
dc.rights.license
Creative Commons Attribution 4.0 International
en
dc.contributor.affiliation
TU Wien, Österreich
-
dc.rights.holder
The Author(s) 2017
-
dc.type.category
Original Research Article
-
tuw.journal.peerreviewed
true
-
tuw.peerreviewed
true
-
tuw.version
vor
-
dcterms.isPartOf.title
INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL
-
tuw.publication.orgunit
E193 - Institut für Softwaretechnik und Interaktive Systeme
-
tuw.publisher.doi
10.1007/s13735-017-0126-y
-
dc.date.onlinefirst
2017-05-25
-
dc.identifier.eissn
2192-662X
-
dc.identifier.libraryid
AC15188642
-
dc.identifier.urn
urn:nbn:at:at-ubtuw:3-4241
-
tuw.author.orcid
0000-0003-0971-4790
-
dc.rights.identifier
CC BY 4.0
de
dc.rights.identifier
CC BY 4.0
en
wb.sci
true
-
item.fulltext
with Fulltext
-
item.cerifentitytype
Publications
-
item.openairecristype
http://purl.org/coar/resource_type/c_2df8fbb1
-
item.languageiso639-1
en
-
item.openaccessfulltext
Open Access
-
item.openairetype
research article
-
item.grantfulltext
open
-
crisitem.author.dept
E193-06 - Forschungsbereich Interactive Media Systems
-
crisitem.author.dept
E193-03 - Forschungsbereich Virtual and Augmented Reality
-
crisitem.author.dept
E000 - Technische Universität Wien
-
crisitem.author.parentorg
E193 - Institut für Visual Computing and Human-Centered Technology
-
crisitem.author.parentorg
E193 - Institut für Visual Computing and Human-Centered Technology