Abstract

Attribute learning has attracted a lot of interests in recent years for its advantage of being able to model high-level concepts with a compact set of midlevel attributes. Real-world objects often demand multiple attributes for effective modeling. Most existing methods learn attributes independently without explicitly considering their intrinsic relatedness. In this paper, we propose max margin multiattribute learning with low-rank constraint, which learns a set of attributes simultaneously, using only relative ranking of the attributes for the data. By learning all the attributes simultaneously through low-rank constraint, the proposed method is able to capture their intrinsic correlation for improved learning; by requiring only relative ranking, the method avoids restrictive binary labels of attributes that are often assumed by many existing techniques. The proposed method is evaluated on both synthetic data and real visual data including a challenging video data set. Experimental results demonstrate the effectiveness of the proposed method.

Original languageEnglish (US)
Article number6811202
Pages (from-to)2866-2876
Number of pages11
JournalIEEE Transactions on Image Processing
Volume23
Issue number7
DOIs
StatePublished - 2014

Fingerprint

Labels

Keywords

  • attribute learning
  • low rank
  • Multi-task learning
  • relative attribute
  • surgical skill

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Max-margin multiattribute learning with low-rank constraint. / Zhang, Qiang; Chen, Lin; Li, Baoxin.

In: IEEE Transactions on Image Processing, Vol. 23, No. 7, 6811202, 2014, p. 2866-2876.

Research output: Contribution to journalArticle

Zhang, Qiang ; Chen, Lin ; Li, Baoxin. / Max-margin multiattribute learning with low-rank constraint. In: IEEE Transactions on Image Processing. 2014 ; Vol. 23, No. 7. pp. 2866-2876.
@article{c062319095a349b2bd82f393b75fd932,
title = "Max-margin multiattribute learning with low-rank constraint",
abstract = "Attribute learning has attracted a lot of interests in recent years for its advantage of being able to model high-level concepts with a compact set of midlevel attributes. Real-world objects often demand multiple attributes for effective modeling. Most existing methods learn attributes independently without explicitly considering their intrinsic relatedness. In this paper, we propose max margin multiattribute learning with low-rank constraint, which learns a set of attributes simultaneously, using only relative ranking of the attributes for the data. By learning all the attributes simultaneously through low-rank constraint, the proposed method is able to capture their intrinsic correlation for improved learning; by requiring only relative ranking, the method avoids restrictive binary labels of attributes that are often assumed by many existing techniques. The proposed method is evaluated on both synthetic data and real visual data including a challenging video data set. Experimental results demonstrate the effectiveness of the proposed method.",
keywords = "attribute learning, low rank, Multi-task learning, relative attribute, surgical skill",
author = "Qiang Zhang and Lin Chen and Baoxin Li",
year = "2014",
doi = "10.1109/TIP.2014.2322446",
language = "English (US)",
volume = "23",
pages = "2866--2876",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Max-margin multiattribute learning with low-rank constraint

AU - Zhang, Qiang

AU - Chen, Lin

AU - Li, Baoxin

PY - 2014

Y1 - 2014

N2 - Attribute learning has attracted a lot of interests in recent years for its advantage of being able to model high-level concepts with a compact set of midlevel attributes. Real-world objects often demand multiple attributes for effective modeling. Most existing methods learn attributes independently without explicitly considering their intrinsic relatedness. In this paper, we propose max margin multiattribute learning with low-rank constraint, which learns a set of attributes simultaneously, using only relative ranking of the attributes for the data. By learning all the attributes simultaneously through low-rank constraint, the proposed method is able to capture their intrinsic correlation for improved learning; by requiring only relative ranking, the method avoids restrictive binary labels of attributes that are often assumed by many existing techniques. The proposed method is evaluated on both synthetic data and real visual data including a challenging video data set. Experimental results demonstrate the effectiveness of the proposed method.

AB - Attribute learning has attracted a lot of interests in recent years for its advantage of being able to model high-level concepts with a compact set of midlevel attributes. Real-world objects often demand multiple attributes for effective modeling. Most existing methods learn attributes independently without explicitly considering their intrinsic relatedness. In this paper, we propose max margin multiattribute learning with low-rank constraint, which learns a set of attributes simultaneously, using only relative ranking of the attributes for the data. By learning all the attributes simultaneously through low-rank constraint, the proposed method is able to capture their intrinsic correlation for improved learning; by requiring only relative ranking, the method avoids restrictive binary labels of attributes that are often assumed by many existing techniques. The proposed method is evaluated on both synthetic data and real visual data including a challenging video data set. Experimental results demonstrate the effectiveness of the proposed method.

KW - attribute learning

KW - low rank

KW - Multi-task learning

KW - relative attribute

KW - surgical skill

UR - http://www.scopus.com/inward/record.url?scp=84901989679&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901989679&partnerID=8YFLogxK

U2 - 10.1109/TIP.2014.2322446

DO - 10.1109/TIP.2014.2322446

M3 - Article

VL - 23

SP - 2866

EP - 2876

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 7

M1 - 6811202

ER -