Video Classification as IR Task: Experiments and Observations

  • Jens Kürsten
  • Maximilian Eibl
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6242)

Abstract

This paper describes experiments we conducted in conjunction with the VideoCLEF 2009 classification task. In our second participation in the task we experimented with treating classification as an IR problem and used the Xtrieval framework [1] to run our experiments. We confirmed that the IR approach achieves strong results although the data set was changed. We proposed an automatic threshold to limit the number of labels per document. Query expansion performed better than the corresponding baseline experiments in terms of mean average precision. We also found that combining the ASR transcriptions and the archival metadata improved the classification performance unless query expansion was used.

Keywords

Ferro 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kürsten, J., Wilhelm, T., Eibl, M.: Extensible Retrieval and Evaluation Framework: Xtrieval. In: Workshop Proceedings of LWA 2008: Lernen - Wissen - Adaption, Würzburg (October 2008)Google Scholar
  2. 2.
    Larson, M., Newman, E., Jones, J.F.G.: Overview of VideoCLEF 2009: New Perspectives on Speech-based Multimedia Content Enrichment. In: CLEF 2009 Workshop, Part II. LNCS, vol. 6242, pp. 354–368. Springer, Heidelberg (2010)Google Scholar
  3. 3.
    Larson, M., Newman, E., Jones, J.F.G.: Overview of VideoCLEF 2008: Automatic Generation of Topic-based Feeds for Dual Language Audio-Visual Content. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 906–917. Springer, Heidelberg (2009)Google Scholar
  4. 4.
    Villena-Román, J., Lana-Serrano, S.: MIRACLE at VideoCLEF 2008: Topic Identification and Keyframe Extraction in Dual Language Videos. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 572–576. Springer, Heidelberg (2009)Google Scholar
  5. 5.
    Newman, E., Jones, G.J.F.: DCU at VideoClef 2008. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 923–926. Springer, Heidelberg (2009)Google Scholar
  6. 6.
    Perea-Ortega, J.M., Montejo-Raéz, A., Martín-Valdivia, M.T.: Using an Information Retrieval System for Video Classification. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 927–930. Springer, Heidelberg (2009)Google Scholar
  7. 7.
    Kürsten, J., Richter, D., Eibl, M.: VideoCLEF 2008: ASR Classification with Wikipedia Categories. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 931–934. Springer, Heidelberg (2009)Google Scholar
  8. 8.
    He, J., Zhang, X., Weerkamp, W., Larson, M.: Metadata and Multilinguality in Video Classification. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 935–938. Springer, Heidelberg (2009)Google Scholar
  9. 9.
    Kürsten, J., Eibl, M.: Chemnitz at VideoCLEF 2009: Experiments and Observations on Treating Classification as IR Task. In: Working Notes for the CLEF 2009 Workshop, Corfu, Greece, September 30-2 October (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jens Kürsten
    • 1
  • Maximilian Eibl
    • 1
  1. 1.Faculty of Computer Science Chair Computer Science and MediaChemnitz University of TechnologyChemnitzGermany

Personalised recommendations