Large Scale Real-Life Action Recognition Using Conditional Random Fields with Stochastic Training

  • Xu Sun
  • Hisashi Kashima
  • Ryota Tomioka
  • Naonori Ueda
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6635)


Action recognition is usually studied with limited lab settings and a small data set. Traditional lab settings assume that the start and the end of each action are known. However, this is not true for the real-life activity recognition, where different actions are present in a continuous temporal sequence, with their boundaries unknown to the recognizer. Also, unlike previous attempts, our study is based on a large-scale data set collected from real world activities. The novelty of this paper is twofold: (1) Large-scale non-boundary action recognition; (2) The first application of the averaged stochastic gradient training with feedback (ASF) to conditional random fields. We find the ASF training method outperforms a variety of traditional training methods in this task.


Continuous Action Recognition Conditional Random Fields Online Training 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    Präkkä, J., Ermes, M., Korpipää, P., Mäntyjärvi, J., Peltola, J., Korhonen, I.: Activity classification using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine 10(1), 119–128 (2006)CrossRefGoogle Scholar
  3. 3.
    Ravi, N., Dandekar, N., Mysore, P., Littman, M.L.: Activity recognition from accelerometer data. In: AAAI, pp. 1541–1546 (2005)Google Scholar
  4. 4.
    Huynh, T., Fritz, M., Schiele, B.: Discovery of activity patterns using topic models. In: Proceedings of the 10th International Conference on Ubiquitous Computing, pp. 10–19. ACM, New York (2008)Google Scholar
  5. 5.
    Nocedal, J., Wright, S.J.: Numerical optimization. Springer, Heidelberg (1999)CrossRefzbMATHGoogle Scholar
  6. 6.
    Bottou, L.: Online algorithms and stochastic approximations. In: Saad, D. (ed.) Online Learning and Neural Networks. Cambridge University Press, Cambridge (1998)Google Scholar
  7. 7.
    Spall, J.C.: Introduction to stochastic search and optimization. Wiley-IEEE (2005)Google Scholar
  8. 8.
    Sun, X., Kashima, H., Matsuzaki, T., Ueda, N.: Averaged stochastic gradient descent with feedback: An accurate, robust and fast training method. In: Proceedings of the 10th International Conference on Data Mining (ICDM 2010), pp. 1067–1072 (2010)Google Scholar
  9. 9.
    Bottou, L.: Une Approche théorique de l’Apprentissage Connexionniste: Applications à la Reconnaissance de la Parole. PhD thesis, Université de Paris XI, Orsay, France (1991)Google Scholar
  10. 10.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning (ICML 2001), pp. 282–289 (2001)Google Scholar
  11. 11.
    Daumé III, H.: Practical Structured Learning Techniques for Natural Language Processing. PhD thesis, University of Southern California (2006)Google Scholar
  12. 12.
    Sun, X.: Efficient Inference and Training for Conditional Latent Variable Models. PhD thesis, The University of Tokyo (2010)Google Scholar
  13. 13.
    Collins, M., Globerson, A., Koo, T., Carreras, X., Bartlett, P.L.: Exponentiated gradient algorithms for conditional random fields and max-margin markov networks. J. Mach. Learn. Res. (JMLR) 9, 1775–1822 (2008)zbMATHGoogle Scholar
  14. 14.
    Collins, M.: Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proceedings of EMNLP 2002, pp. 1–8 (2002)Google Scholar
  15. 15.
    Hattori, Y., Takemori, M., Inoue, S., Hirakawa, G., Sudo, O.: Operation and baseline assessment of large scale activity gathering system by mobile device. In: Proceedings of DICOMO 2010 (2010)Google Scholar
  16. 16.
    Andrew, G., Gao, J.: Scalable training of L 1-regularized log-linear models. In: Proceedings of ICML 2007, pp. 33–40 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Xu Sun
    • 1
  • Hisashi Kashima
    • 1
  • Ryota Tomioka
    • 1
  • Naonori Ueda
    • 2
  1. 1.Department of Mathematical InformaticsThe University of TokyoJapan
  2. 2.NTT Communication Science LaboratoriesKyotoJapan

Personalised recommendations