Learning the consensus on visual quality for next-generation image management

Ritendra Datta, Jia Li, James Z. Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

36 Citations (Scopus)

Abstract

While personal and community-based image collections grow by the day, the demand for novel photo management capabilities grows with it. Recent research has shown that it is possible to learn the consensus on visual quality measures such as aesthetics with a moderate degree of success. Here, we seek to push this performance to more realistic levels and use it to (a) help select high-quality pictures from collections, and (b) eliminate low-quality ones, introducing appropriate performance metrics in each case. To achieve this, we propose a sequential arrangement of a weighted linear least squares regressor and a naive Bayes' classifier, applied to a set of visual features previously found useful for quality prediction. Experiments on real-world data for these tasks show promising performance, with significant improvements over a previously proposed SVM-based method.

Original languageEnglish (US)
Title of host publicationProceedings of the Fifteenth ACM International Conference on Multimedia, MM'07
Pages533-536
Number of pages4
DOIs
StatePublished - Dec 1 2007
Event15th ACM International Conference on Multimedia, MM'07 - Augsburg, Bavaria, Germany
Duration: Sep 24 2007Sep 29 2007

Publication series

NameProceedings of the ACM International Multimedia Conference and Exhibition

Other

Other15th ACM International Conference on Multimedia, MM'07
CountryGermany
CityAugsburg, Bavaria
Period9/24/079/29/07

Fingerprint

Classifiers
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Datta, R., Li, J., & Wang, J. Z. (2007). Learning the consensus on visual quality for next-generation image management. In Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07 (pp. 533-536). (Proceedings of the ACM International Multimedia Conference and Exhibition). https://doi.org/10.1145/1291233.1291364
Datta, Ritendra ; Li, Jia ; Wang, James Z. / Learning the consensus on visual quality for next-generation image management. Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07. 2007. pp. 533-536 (Proceedings of the ACM International Multimedia Conference and Exhibition).
@inproceedings{d350b9f77b34455b97a0c5c6c19dbe76,
title = "Learning the consensus on visual quality for next-generation image management",
abstract = "While personal and community-based image collections grow by the day, the demand for novel photo management capabilities grows with it. Recent research has shown that it is possible to learn the consensus on visual quality measures such as aesthetics with a moderate degree of success. Here, we seek to push this performance to more realistic levels and use it to (a) help select high-quality pictures from collections, and (b) eliminate low-quality ones, introducing appropriate performance metrics in each case. To achieve this, we propose a sequential arrangement of a weighted linear least squares regressor and a naive Bayes' classifier, applied to a set of visual features previously found useful for quality prediction. Experiments on real-world data for these tasks show promising performance, with significant improvements over a previously proposed SVM-based method.",
author = "Ritendra Datta and Jia Li and Wang, {James Z.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1145/1291233.1291364",
language = "English (US)",
isbn = "9781595937025",
series = "Proceedings of the ACM International Multimedia Conference and Exhibition",
pages = "533--536",
booktitle = "Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07",

}

Datta, R, Li, J & Wang, JZ 2007, Learning the consensus on visual quality for next-generation image management. in Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07. Proceedings of the ACM International Multimedia Conference and Exhibition, pp. 533-536, 15th ACM International Conference on Multimedia, MM'07, Augsburg, Bavaria, Germany, 9/24/07. https://doi.org/10.1145/1291233.1291364

Learning the consensus on visual quality for next-generation image management. / Datta, Ritendra; Li, Jia; Wang, James Z.

Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07. 2007. p. 533-536 (Proceedings of the ACM International Multimedia Conference and Exhibition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Learning the consensus on visual quality for next-generation image management

AU - Datta, Ritendra

AU - Li, Jia

AU - Wang, James Z.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - While personal and community-based image collections grow by the day, the demand for novel photo management capabilities grows with it. Recent research has shown that it is possible to learn the consensus on visual quality measures such as aesthetics with a moderate degree of success. Here, we seek to push this performance to more realistic levels and use it to (a) help select high-quality pictures from collections, and (b) eliminate low-quality ones, introducing appropriate performance metrics in each case. To achieve this, we propose a sequential arrangement of a weighted linear least squares regressor and a naive Bayes' classifier, applied to a set of visual features previously found useful for quality prediction. Experiments on real-world data for these tasks show promising performance, with significant improvements over a previously proposed SVM-based method.

AB - While personal and community-based image collections grow by the day, the demand for novel photo management capabilities grows with it. Recent research has shown that it is possible to learn the consensus on visual quality measures such as aesthetics with a moderate degree of success. Here, we seek to push this performance to more realistic levels and use it to (a) help select high-quality pictures from collections, and (b) eliminate low-quality ones, introducing appropriate performance metrics in each case. To achieve this, we propose a sequential arrangement of a weighted linear least squares regressor and a naive Bayes' classifier, applied to a set of visual features previously found useful for quality prediction. Experiments on real-world data for these tasks show promising performance, with significant improvements over a previously proposed SVM-based method.

UR - http://www.scopus.com/inward/record.url?scp=37849034092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37849034092&partnerID=8YFLogxK

U2 - 10.1145/1291233.1291364

DO - 10.1145/1291233.1291364

M3 - Conference contribution

AN - SCOPUS:37849034092

SN - 9781595937025

T3 - Proceedings of the ACM International Multimedia Conference and Exhibition

SP - 533

EP - 536

BT - Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07

ER -

Datta R, Li J, Wang JZ. Learning the consensus on visual quality for next-generation image management. In Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07. 2007. p. 533-536. (Proceedings of the ACM International Multimedia Conference and Exhibition). https://doi.org/10.1145/1291233.1291364