Attribute constrained subspace learning

Mohammadreza Babaee; Maryam Babaei; Daniel Merget; Philipp Tiefenbacher; Gerhard Rigoll

doi:10.1109/ICIP.2015.7351544

Attribute constrained subspace learning

Mohammadreza Babaee, Maryam Babaei, Daniel Merget, Philipp Tiefenbacher, Gerhard Rigoll

Chair of Human-Machine Communication

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Visual attributes are high-level semantic descriptions of visual data that are close to the human language. They have been used intensively in various applications such as image classification, active learning, and interactive search. However, the usage of attributes in subspace learning (or dimensionality reduction) has not been considered yet. In this work, we propose to utilize relative attributes as semantic cues in subspace learning. To this end, we employ Non-negative Matrix Factorization (NMF) constrained by embedded relative attributes to learn a subspace representation of image content. Experiments conducted on two datasets show the efficiency of attributes in discriminative subspace learning.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Publisher	IEEE Computer Society
Pages	3941-3945
Number of pages	5
ISBN (Electronic)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7351544
State	Published - 9 Dec 2015
Event	IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: 27 Sep 2015 → 30 Sep 2015

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2015-December
ISSN (Print)	1522-4880

Conference

Conference	IEEE International Conference on Image Processing, ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	27/09/15 → 30/09/15

Keywords

Subspace learning
non-negative matrix factorization
relative attributes

Access to Document

10.1109/ICIP.2015.7351544

Cite this

Babaee, M., Babaei, M., Merget, D., Tiefenbacher, P., & Rigoll, G. (2015). Attribute constrained subspace learning. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings (pp. 3941-3945). Article 7351544 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December). IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351544

@inproceedings{9f734def6c8a470b8a2afed89dd35c2e,

title = "Attribute constrained subspace learning",

abstract = "Visual attributes are high-level semantic descriptions of visual data that are close to the human language. They have been used intensively in various applications such as image classification, active learning, and interactive search. However, the usage of attributes in subspace learning (or dimensionality reduction) has not been considered yet. In this work, we propose to utilize relative attributes as semantic cues in subspace learning. To this end, we employ Non-negative Matrix Factorization (NMF) constrained by embedded relative attributes to learn a subspace representation of image content. Experiments conducted on two datasets show the efficiency of attributes in discriminative subspace learning.",

keywords = "Subspace learning, non-negative matrix factorization, relative attributes",

author = "Mohammadreza Babaee and Maryam Babaei and Daniel Merget and Philipp Tiefenbacher and Gerhard Rigoll",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Conference on Image Processing, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7351544",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3941--3945",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

}

Babaee, M, Babaei, M, Merget, D, Tiefenbacher, P & Rigoll, G 2015, Attribute constrained subspace learning. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings., 7351544, Proceedings - International Conference on Image Processing, ICIP, vol. 2015-December, IEEE Computer Society, pp. 3941-3945, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7351544

Attribute constrained subspace learning. / Babaee, Mohammadreza; Babaei, Maryam; Merget, Daniel et al.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. IEEE Computer Society, 2015. p. 3941-3945 7351544 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Attribute constrained subspace learning

AU - Babaee, Mohammadreza

AU - Babaei, Maryam

AU - Merget, Daniel

AU - Tiefenbacher, Philipp

AU - Rigoll, Gerhard

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Visual attributes are high-level semantic descriptions of visual data that are close to the human language. They have been used intensively in various applications such as image classification, active learning, and interactive search. However, the usage of attributes in subspace learning (or dimensionality reduction) has not been considered yet. In this work, we propose to utilize relative attributes as semantic cues in subspace learning. To this end, we employ Non-negative Matrix Factorization (NMF) constrained by embedded relative attributes to learn a subspace representation of image content. Experiments conducted on two datasets show the efficiency of attributes in discriminative subspace learning.

AB - Visual attributes are high-level semantic descriptions of visual data that are close to the human language. They have been used intensively in various applications such as image classification, active learning, and interactive search. However, the usage of attributes in subspace learning (or dimensionality reduction) has not been considered yet. In this work, we propose to utilize relative attributes as semantic cues in subspace learning. To this end, we employ Non-negative Matrix Factorization (NMF) constrained by embedded relative attributes to learn a subspace representation of image content. Experiments conducted on two datasets show the efficiency of attributes in discriminative subspace learning.

KW - Subspace learning

KW - non-negative matrix factorization

KW - relative attributes

UR - http://www.scopus.com/inward/record.url?scp=84956655014&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351544

DO - 10.1109/ICIP.2015.7351544

M3 - Conference contribution

AN - SCOPUS:84956655014

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3941

EP - 3945

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE Computer Society

T2 - IEEE International Conference on Image Processing, ICIP 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Attribute constrained subspace learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this