Advertisement

Modeling and Analysis of Dynamic Behaviors of Web Image Collections

  • Gunhee Kim
  • Eric P. Xing
  • Antonio Torralba
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)

Abstract

Can we model the temporal evolution of topics in Web image collections? If so, can we exploit the understanding of dynamics to solve novel visual problems or improve recognition performance? These two challenging questions are the motivation for this work. We propose a nonparametric approach to modeling and analysis of topical evolution in image sets. A scalable and parallelizable sequential Monte Carlo based method is developed to construct the similarity network of a large-scale dataset that provides a base representation for wide ranges of dynamics analysis. In this paper, we provide several experimental results to support the usefulness of image dynamics with the datasets of 47 topics gathered from Flickr. First, we produce some interesting observations such as tracking of subtopic evolution and outbreak detection, which cannot be achieved with conventional image sets. Second, we also present the complementary benefits that the images can introduce over the associated text analysis. Finally, we show that the training using the temporal association significantly improves the recognition performance.

Keywords

Visual Word Cosine Similarity Temporal Context Similarity Network Sequential Monte Carlo 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A Tutorial on Particle Filters for On-line Non-linear/Non-Gaussian Bayesian Tracking. IEEE Trans. Signal Processing 50(2), 174–188 (2002)CrossRefGoogle Scholar
  2. 2.
    Becker, S.: Implicit Learning in 3D Object Recognition: The Importance of Temporal Context. Neural Computation 11(2), 347–374 (1999)CrossRefGoogle Scholar
  3. 3.
    Blei, D.M., Lafferty, J.D.: Dynamic Topic Models. In: ICML (2006)Google Scholar
  4. 4.
    Bosch, A., Zisserman, A., Munoz, X.: Image Classification using Random Forests and Ferns. In: ICCV (2007)Google Scholar
  5. 5.
    Boutell, M., Luo, J., Brown, C.: A Generalized Temporal Context Model for Classifying Image Collections. Multimedia Systems 11(1), 82–92 (2005)CrossRefGoogle Scholar
  6. 6.
    Cao, L., Luo, J., Kautz, H., Huang, T.S.: Annotating Collections of Photos using Hierarchical Event and Scene Models. In: CVPR (2008)Google Scholar
  7. 7.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge, VOC 2010 Results (2010), http://www.pascal-network.org/challenges/VOC/voc2010/workshop/index.html
  8. 8.
    Hinton, G.E.: Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation 14(8), 1771–1800 (2002)zbMATHCrossRefGoogle Scholar
  9. 9.
    Isard, M., Blake, A.: CONDENSATION – Conditional Density Propagation for Visual Tracking. Int. J. Computer Vision 29(1), 5–28 (1998)CrossRefGoogle Scholar
  10. 10.
    Kalogerakis, E., Vesselova, O., Hays, J., Efros, A., Hertzmann, A.: Image Sequence Geolocation with Human Travel Priors. In: ICCV (2009)Google Scholar
  11. 11.
    Kim, G., Torralba, A.: Unsupervised Detection of Regions of Interest using Iterative Link Analysis. In: NIPS (2009)Google Scholar
  12. 12.
    Li, Y., Crandall, D.J., Huttenlocher, D.P.: Landmark Classification in Large-scale Image Collections. In: ICCV (2009)Google Scholar
  13. 13.
    Liu, C., Yuen, J., Torralba, A.: Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment. In: CVPR (2009)Google Scholar
  14. 14.
    Liu, C., Yuen, J., Torralba, A., Sivic, J., Freeman, W.T.: SIFT Flow: Dense Correspondence across Different Scenes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 28–42. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    MacKay, D.: Information Theory, Inference and Learning Algorithms. Cambridge University Press, Cambridge (2002)Google Scholar
  16. 16.
    Paletta, L., Prantl, M., Pinz, A.: Learning Temporal Context in Active Object Recognition Using Bayesian Analysis. In: ICPR (2000)Google Scholar
  17. 17.
    Quack, T., Leibe, B., Gool, L.V.: World-scale Mining of Objects and Events from Community Photo Collections. In: CIVR (2008)Google Scholar
  18. 18.
    Russell, B.C., Torralba, A.: Building a Database of 3D Scenes from User Annotations. In: CVPR (2009)Google Scholar
  19. 19.
    Sinha, P., Balas, B., Ostrovsky, Y., Russell, R.: Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About. Proceedings of the IEEE 94(11), 1948–1962 (2006)CrossRefGoogle Scholar
  20. 20.
    Torralba, A., Fergus, R., Freeman, W.T.: 80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition. IEEE PAMI 30(11), 1958–1970 (2008)Google Scholar
  21. 21.
    Wallis, G., Bulthöff, H.H.: Effects of Temporal Association on Recognition Memory. PNAS 98(8), 4800–4804 (2001)CrossRefGoogle Scholar
  22. 22.
    Wang, X., McCallum, A.: Topics Over Time: a Non-Markov Continuous-Time Model of Topical Trends. In: KDD (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Gunhee Kim
    • 1
  • Eric P. Xing
    • 1
  • Antonio Torralba
    • 2
  1. 1.Carnegie Mellon UniversityPittsburghUSA
  2. 2.Massachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations