Analyzing Diving: A Dataset for Judging Action Quality

  • Kamil Wnuk
  • Stefano Soatto
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6468)


This work presents a unique new dataset and objectives for action analysis. The data presents 3 key challenges: tracking, classification, and judging action quality. The last of these, to our knowledge, has not yet been attempted in the vision literature as applied to sports where technique is scored.

This work performs an initial analysis of the dataset with classification experiments, confirming that temporal information is more useful than holistic bag-of-features style analysis in distinguishing dives. Our investigation lays a groundwork of effective tools for working with this type of sports data for future investigations into judging the quality of actions.


Background Subtraction Foreground Object Motion Blur Human Action Recognition Background Subtraction Method 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rodriguez, M., Ahmed, J., Shah, M.: Action mach: A spatio-temporal maximum average correlation height filter for action recognition. In: Proc. CVPR (2008)Google Scholar
  2. 2.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 2, 91–110 (2004)CrossRefGoogle Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histogram of oriented gradients for human detection. In: Proc. CVPR (2005)Google Scholar
  4. 4.
    Felzenszwalb, P., Girshick, D., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI (2010)Google Scholar
  5. 5.
    Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: Proc. ICCV (2003)Google Scholar
  6. 6.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local svm approach. In: Proc. ICPR (2004)Google Scholar
  7. 7.
    Yeffet, L., Wolf, L.: Local trinary patterns for human action recognition. In: Proc. ICCV (2009)Google Scholar
  8. 8.
    Wilson, A., Bobick, A.: Parametric hidden markov models for gesture recognition. PAMI 21 (1999)Google Scholar
  9. 9.
    Raptis, M., Wnuk, K., Soatto, S.: Flexible dictionaries for action recognition. In: Proceedings of the 1st International Workshop on Machine Learning for Vision-based Motion Analysis, in conjunction with ECCV (2008)Google Scholar
  10. 10.
    Saad, A., Arslan, B., Mubarak, S.: Chaotic invariants for human action recognition. In: IEEE 11th International Conference on Computer Vision, pp. 1–8 (2007)Google Scholar
  11. 11.
    Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proc. CVPR (2008)Google Scholar
  12. 12.
    Fischler, M., Bolles, R.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. of the ACM. 24, 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Ko, T., Soatto, S., Estrin, D.: Background subtraction on distributions. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 276–289. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  14. 14.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008),
  15. 15.
    Shimodaira, H., Noma, K.I., Nakai, M., Sagayama, S.: Dynamic time alignment kernel in support vector machine. In: Proc. NIPS (2002)Google Scholar
  16. 16.
    Zhou, F., De la Torre, F., Hodgins, J.K.: Aligned cluster analysis for temporal segmentation of human motion. In: IEEE Conference on Automatic Face and Gestures Recognition (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Kamil Wnuk
    • 1
  • Stefano Soatto
    • 1
  1. 1.University of CaliforniaLos AngelesUSA

Personalised recommendations