Automated Multimedia Diaries of Mobile Device Users Need Summarization

  • M. Gelgon
  • K. Tilhou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2411)


This paper addresses a still original issue and a solution that, while emerging from the pattern recognition point of view, certainly shares common goals with mobile HCI research goals. The contribution is at the crossroads of multimedia data analysis for content-based retrieval, and wearable computing. As users are acquiring multimedia content personal mobile devices, they are getting also undergoing information overflow. The problem of structuring the content into time-oriented meaningful episodes is addressed, and we argue that geographical location processing is crucial, as a complement to processing audiovisual material. A technique for model-based temporal structuring of one’s trajectory during a day is presented, based on a Bayesian/MAP approach, that generates one or several summaries. Experimental results illustrate the applicative interest of the problem addressed and validates the proposed solution


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    G.D. Abowd and E.D. Mynatt. Charting past, present and future research in ubiquitous computing. ACM Trans. on Computer-Human Interaction, 7(1):29–58, March 2000.Google Scholar
  2. 2.
    K. Aizawa, K. Ishijima, and M. Shiina. Summarizing wearable video. In IEEE. Int. Conf. on Image Processing (ICIP’2001), pages 453–457, Thessaloniki, Greece, september 2001.Google Scholar
  3. 3.
    D. Ashbrook and T. Starner. Learning significant locations and predicting user movement with gps. In To appear in IEEE Int. Symp. on Wearable Computer, oct 2002.Google Scholar
  4. 4.
    C. Biernacki, G. Celeux, and G. Govaert. Strategies for getting the largest likelihood in mixture models. In ASA Joint Statistical Meeting JSM 2000, invited paper, Indianapolis, USA, 2000.Google Scholar
  5. 5.
    O Buyuk0kokten, H. Garcia-Molina, and A. Paepcke. Accordion summarization for end-game browsing on pdas and cellular phones. In Proc. of ACM Computer Human Interaction (CHI’2001), Seattle, Washington, USA, 2001.Google Scholar
  6. 6.
    B. Clarkson and A. Pentland. Predicting daily behavior via wearable sensors. Technical Report Vismod TR 451, MIT, July 2001.Google Scholar
  7. 7.
    G.M. Djuknic and R.E. Richton. Geolocation and assisted GPS. IEEE Computer, pages 123–125, February 2001.Google Scholar
  8. 8.
    M. Gelgon. Using face detection for browsing personal slow video in a small terminal and worn camera context. In IEEE. Int. Conf. on Image Processing (ICIP’2001), pages 1062–1065, Thessaloniki, Greece, september 2001.Google Scholar
  9. 9.
    M. Gelgon and P. Bouthemy. Determining a structured spatio-temporal representation of video content for efficient visualisation and indexing. In 5th European Conference on Computer Vision (ECCV’98), LNCS 1406-1407, pages 595–609 (II), Freiburg, Germany, June 1998.Google Scholar
  10. 10.
    T. Haddrell and T. Pratt. Understanding the indoor GPS signal. In Institute Of Navigation ION-GPS 2001 Conference, pages 123–129, Salt Lake City, USA, September 2001.Google Scholar
  11. 11.
    M.H. Hansen and B. Yu. Model selection and the principle of minimum description length. Journal of the American Statistical Association (JASA), 96(454):746–774, 2001.MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    E. Keogh, S. Chu, D. Hart, and M. Pazzani. An online algorithm for segmenting time-series. In IEEE International Conference on Data Mining, Silicon Valley, USA, December 2001.Google Scholar
  13. 13.
    M. Lamming and M. Flynn. Forget-me-not: intimate computing in support of human memory. In Procs. of Friend21: Int. Symp. on next generation human interface, pages 124–128, Meguro Gajoen, Japan, 1994.Google Scholar
  14. 14.
    J. Luo, A.E. Savakis, and A. Etz, S. Singhal. On the application of Bayes networks to semantic understanding of consumer photographs. In IEEE. Int. Conf. on Image Processing (ICIP’2000), pages 802–807, Vancouver, Canada, september 2000.Google Scholar
  15. 15.
    N. Marmasse and C. Schmandt. Location-aware information delivery. In IEEE Int. Symposium on handheld and ubiquitous computing, pages 157–171, Bristol, U.K., sep 2000.Google Scholar
  16. 16.
    J. Oliver and C. Forbes. Bayesian approaches to segmenting a simple time series. In Proc. of Proceedings of the Econometric Society Australasian Meeting, C. L. Skeels (ed), Canberry, 1998.Google Scholar
  17. 17.
    R.A. Redner and H.F Walker. Mixture densities, maximum likelihood and the EM algorithm. Society for Industrial and Applied Mathematics-SIAM Review, 26(2):195–239, 1984.MATHMathSciNetGoogle Scholar
  18. 18.
    B. Rhodes. The wearable rememberance agent: a system for augmented memory. Personal Technologies Journal-Special issue on wearable computing, 1(4):218–224, 1997.Google Scholar
  19. 19.
    S.J. Roberts, R. Everson, and I. Rezek. Minimum entropy data partitioning. Proc. International Conference on Artificial Neural Networks, 2:844–849, 1999.CrossRefGoogle Scholar
  20. 20.
    M.A Smith and T. Kanade. Video skimming and characterization through the combination of image and language understanding techniques. In Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, pages 775–781, Puerto-Rico, juin 1997.Google Scholar
  21. 21.
    T. Starner, B. Schiele, and A. Pentland. Visual contextual awareness in wearable computing. In IEEE Int. Symp. on Wearable Computing, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • M. Gelgon
    • 1
  • K. Tilhou
    • 1
  1. 1.IRIN/Ecole polytechnique de l’université de NantesNantes cedex 3France

Personalised recommendations