On the significance of cluster-temporal browsing for generic video retrieval: a statistical analysis

ABSTRACT

In this paper, we test statistically the effect of content-based browsing in generic video retrieval. Using TRECVID 2004 and 2005 experiments, we demonstrate that content-based browsing improves retrieval over sequential queries and relevance feedback. Two user groups, novices and system developers have been used in the experiments on large and multilingual video collections. Novice users were found to achieve improvement in search effectiveness with cluster-temporal browsing by statistically significant amount. System developers did not have statistically significant difference between the different system configurations.

REFERENCES

• 1: Justin Zobel, How reliable are the results of large-scale information retrieval experiments?, Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, p.307-314, August 24-28, 1998, Melbourne, Australia [doi>10.1145/290941.291014]
• 2: Salton, G., and Buckley, C. Improving retrieval performance by relevance feedback. Journal of the American Society for Information Science, vol. 41, 1990, pp. 288--297.
• 3: Alexander G. Hauptmann , Michael G. Christel, Successful approaches in the TREC video retrieval evaluations, Proceedings of the 12th annual ACM international conference on Multimedia, October 10-16, 2004, New York, NY, USA [doi>10.1145/1027527.1027681]
• 4: Kraaij, W., Smeaton, A.F., Over, P., and Arlandis, J. TRECVID 2004 - an overview. Online Proceedings of the TRECVID 2004, Gaithersburg, MD, United States, 2004, http://wwwnlpir.nist.gov/projects/tvpubs/tv.pubs.org.html.
• 5: Rautiainen, M., Seppänen, T., and Ojala, T. Advancing content-based retrieval effectiveness with cluster-temporal browsing in multilingual video databases. IEEE Int. Conf. on Multimedia & Expo, Toronto, Canada, 2006, 377--380.
• 6: Rautiainen, M., Varanka, M., Hanski, I., Hosio, M., Pramila, A., Liu, J., Ojala, T., and Seppänen, T. TRECVID 2005 Experiments at MediaTeam Oulu. TREC Video Retrieval Evaluation Online Proc., TRECVID '05, Gaithersburg, MD.
• 7: Mika Rautiainen , Timo Ojala , Tapio Seppänen, Analysing the performance of visual, concept and text features in content-based video retrieval, Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval, October 15-16, 2004, New York, NY, USA [doi>10.1145/1026711.1026744]
• 8: Girgensohn, A., Adcock, J., Cooper, M., Wilcox, L. A Synergistic Approach to Efficient Interactive Video Retrieval. INTERACT 2005, LNCS 3585, 2005, 781--794.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Query formulation

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models; Search process
      H.3.4 Systems and Software
          Subjects: Performance evaluation (efficiency and effectiveness)

General Terms:
Algorithms, Experimentation, Performance, Verification

Keywords:
Wilcoxon's signed-rank test, cluster-temporal browsing, content-based video retrieval, non-parametric test