Advertisement

There Is More Than One Way to Get Out of a Car: Automatic Mode Finding for Action Recognition in the Wild

  • Olusegun Oshin
  • Andrew Gilbert
  • Richard Bowden
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6669)

Abstract

“Actions in the wild” is the term given to examples of human motion that are performed in natural settings, such as those harvested from movies [10] or the Internet [9]. State-of-the-art approaches in this domain are orders of magnitude lower than in more contrived settings. One of the primary reasons being the huge variability within each action class. We propose to tackle recognition in the wild by automatically breaking complex action categories into multiple modes/group, and training a separate classifier for each mode. This is achieved using RANSAC which identifies and separates the modes while rejecting outliers. We employ a novel reweighting scheme within the RANSAC procedure to iteratively reweight training examples, ensuring their inclusion in the final classification model. Our results demonstrate the validity of the approach, and for classes which exhibit multi-modality, we achieve in excess of double the performance over approaches that assume single modality.

Keywords

Action Recognition Average Precision Interest Point Action Execution Random Sampling Consensus 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: VS-PETS, pp. 65–72 (2005)Google Scholar
  2. 2.
    Fischler, M.A., Bolles, R.C.: Ransac: A paradigm for model fitting with applications to image analysis and automated cartography. Comms. of the ACM 24(6), 381–395 (1981)CrossRefGoogle Scholar
  3. 3.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23–37. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  4. 4.
    Gilbert, A., Illingworth, J., Bowden, R.: Action recognition using mined hierarchical compound features. PAMI 99(PrePrints) (2010)Google Scholar
  5. 5.
    Han, D., Bo, L., Sminchisescu, C.: Selection and context for action recognition. In: ICCV, pp. 1–8 (2009)Google Scholar
  6. 6.
    Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, pp. 1–8 (2008)Google Scholar
  7. 7.
    Laptev, I., Perez, P.: Retrieving actions in movies. In: ICCV, pp. 1–8 (2007)Google Scholar
  8. 8.
    Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos ”in the wild”. In: CVPR, pp. 1–8 (2009)Google Scholar
  9. 9.
    Liu, J., Shah, M.: Learning human actions via information maximization. In: CVPR, pp. 1–8 (2008)Google Scholar
  10. 10.
    Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR, pp. 1–8 (2009)Google Scholar
  11. 11.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local SVM approach. In: ICPR, pp. 32–36 (2004)Google Scholar
  12. 12.
    Szepannek, G., Schiffner, J., Wilson, J., Weihs, C.: Local modelling in classification. In: Perner, P. (ed.) ICDM 2008. LNCS (LNAI), vol. 5077, pp. 153–164. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  13. 13.
    Ullah, M.M., Parizi, S.N., Laptev, I.: Improving bag-of-features action recognition with non-local cues. In: BMVC, pp. 95.1–95.11 (2010)Google Scholar
  14. 14.
    Urtasun, R., Darrell, T.: Sparse probabilistic regression for activity-independent human pose inference. In: CVPR (2008)Google Scholar
  15. 15.
    Zhang, H., Berg, A.C., Maire, M., Malik, J.: Svm-knn: Discriminative nearest neighbor classification for visual category recognition. In: CVPR, pp. 2126–2136 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Olusegun Oshin
    • 1
  • Andrew Gilbert
    • 1
  • Richard Bowden
    • 1
  1. 1.Centre for Vision, Speech and Signal ProcessingUniversity of SurreyGuildfordUnited Kingdom

Personalised recommendations