skip to main content
10.1145/1743384.1743479acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
poster

Minimum explanation complexity for MOD based visual concept detection

Published: 29 March 2010 Publication History

Abstract

Visual concept detection in images has been a challenging task for many years. The recently proposed MIRFLICKR-25000 dataset has set the standards even higher as the wide variety of images and annotations require new techniques to tackle the visual concept detection problem. We propose the use of the recently introduced MOD salient points for subimage visual concept detection. These points are located at regions within an image that are distinctive with respect to the features that are selected for subimage classification. We also introduce the notion of Minimum Explanation Complexity (MEC), where the complexity of classifiers is reduced to a simpler but equally effective form whenever possible. Our experiments on the MIRFLICKR-25000 dataset show that MOD based concept detectors outperform SIFT based features. We also show that a neural network classifier based on the MEC notion, outperforms a standard SVM classifier.

References

[1]
Blighe, M. and O'Connor, N. E. 2008. MyPlaces: detecting important settings in a visual diary. Proceedings of the 2008 international conference on Content-based image and video retrieval, Niagara Falls, Canada, July 2008, 195--204.
[2]
Cao, L. Luo, J. Kautz H. and Huang, T. S. 2008. Annotating collections of photos using hierarchical event and scene models.IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, June 2008, 1--8.
[3]
Chang, C.-C. and Lin, .C.-J. 2001. LIBSVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[4]
Datta, R., Joshi, D., et al. 2008. Image Retrieval: Ideas, Influences, and Trends of the New Age. ACM Computing Surveys, vol. 40, no. 2, article 5, 1--60.
[5]
Douze, M., Guillaumin, M. et al. 2009. INRIA-LEARs participation to ImageCLEF 2009. CLEF working 2009, Corfu, Greece.
[6]
Forsyth, D., Mundy, J. S., et al. 1991. Invariant Descriptors for 3-D Object Recognition and Pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, 971--991.
[7]
Harwood, D., Ojala, T., et al. 1993. Texture classification by center-symmetric auto-correlation, sing Kullback discrimination of distributions. Technical report CARTR678, Computer Vision Laboratory, Center for Automation Research, University of Maryland, College Park, Maryland.
[8]
Huiskes, M. J. and Lew, M. S. 2008. Performance evaluation of relevance feedback methods. ACM International Conference on Video and Image Retrieval (CIVR'08), Niagara Falls, Canada, July 2008, 239--248.
[9]
Lew, M. S. 2000. Next-generation Web Searches for Visual Content, IEEE Computer, 46--53.
[10]
Lew, M. S., Sebe, N., et al. 2006. Content-based Multimedia Information Retrieval: State of the Art and Challenges. ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 2, issue 1, 1--19.
[11]
Li J. and Wang, J. Z. 2006. Real-time Computerized Annotation of Pictures. Proceedings of the ACM Multimedia Conference, Santa Barbara, CA, October 2006, 911--920.
[12]
Lowe, D. G. 2004. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, vol. 60, issue 2, 91--110.
[13]
Ngiam J. and Goh, H. 2009. I2R ImageCLEF Photo Annotation 2009 Working Notes. CLEF working notes 2009, Corfu, Greece.
[14]
Oerlemans, A. and Lew, M. S. 2008. Interest points based on maximization of distinctiveness. Proceedings of ACM International Conference on Multimedia Information Retrieval, Vancouver, Canada, October 2008, 202--207.
[15]
Ojala, T., Pietikäinen, M. and Harwood, D. 1996. A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, volume 29, 51--59.
[16]
Rissanen, J. 1978. Modeling By Shortest Data Description. Automatica, vol. 14, 465--471.
[17]
Sebe, N., Lew, M. S. 2001. Color-based Retrieval. Pattern Recognition Letters, vol. 22, 223--230.
[18]
Sebe, N., Lew, M. S. 2001. Texture Features for Content-Based retrieval. In Principles of Visual Information Retrieval, (M. S. Lew, ed.), Springer, 51--86.
[19]
Sebe, N. and Lew, M. S. 2000. Wavelet Based Texture Classification. In Proceedings of the 15th International Conference on Pattern Recognition (ICPR), vol. III, Barcelona, Spain, September 2000, 959--962.
[20]
Tuffield, M., Harris, S., et al. 2006. Image annotation with Photocopain. In First International Workshop on Semantic Web Annotations for Multimedia (SWAMM 2006) at WWW2006, May 2006, Edinburgh, United Kingdom.
[21]
Van de Sande, K. E. A., Gevers, T. and Smeulders, A. W. M. 2009. The University of Amsterdam's Concept Detection System at ImageCLEF 2009. CLEF working notes 2009, Corfu, Greece.
[22]
Wallace C. S. and Boulton, D. M. 1968. An information measure for classification. Computer Journal, vol. 11, issue 2, 185--194.
[23]
Young, S. S., Scott, P. D. and Nasrabadi, N. M. 1994. Object Recognition using Multi-Layer Hopfield Neural Network. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Seattle, WA, June 1994, 417--422.

Cited By

View all
  • (2012)The leiden augmented reality system (LARS)Proceedings of the 12th international conference on Computer Vision - Volume Part III10.1007/978-3-642-33885-4_71(639-642)Online publication date: 7-Oct-2012
  • (2011)RetrievalLabProceedings of the 1st ACM International Conference on Multimedia Retrieval10.1145/1991996.1992067(1-2)Online publication date: 18-Apr-2011

Index Terms

  1. Minimum explanation complexity for MOD based visual concept detection

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    MIR '10: Proceedings of the international conference on Multimedia information retrieval
    March 2010
    600 pages
    ISBN:9781605588155
    DOI:10.1145/1743384
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 29 March 2010

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. feature extraction
    2. local distinctiveness
    3. salient points
    4. visual concept detection

    Qualifiers

    • Poster

    Conference

    MIR '10
    Sponsor:
    MIR '10: International Conference on Multimedia Information Retrieval
    March 29 - 31, 2010
    Pennsylvania, Philadelphia, USA

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)0
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 21 Jan 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2012)The leiden augmented reality system (LARS)Proceedings of the 12th international conference on Computer Vision - Volume Part III10.1007/978-3-642-33885-4_71(639-642)Online publication date: 7-Oct-2012
    • (2011)RetrievalLabProceedings of the 1st ACM International Conference on Multimedia Retrieval10.1145/1991996.1992067(1-2)Online publication date: 18-Apr-2011

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media