Abstract
Applications of unsupervised learning techniques to action recognition have proved highly competitive in comparison to supervised and hand-crafted approaches, despite not being designed to handle image processing problems. Many of these techniques are either based on biological models of cognition or have responses that correlate to those observed in biological systems. In this study we apply (for the first time) an adaptation of the latest hierarchical temporal memory (HTM) cortical learning algorithms (CLAs) to the problem of action recognition. These HTM algorithms are both unsupervised and represent one of the most complete high-level syntheses available of the current neuroscientific understanding of the functioning of neocortex.
Specifically, we extend the latest HTM work on augmented spatial pooling, to produce a fixed frame temporal pooler (FFTP). This pooler is evaluated on the well-known KTH action recognition data set and in comparison with the best performing unsupervised learning algorithm for bag-of-features classification in the area: independent subspace analysis (ISA). Our results show FFTP comes within 2% of ISA’s performance and outperforms other comparable techniques on this data set. We take these results to be promising, given the preliminary nature of the research and that the FFTP algorithm is only a partial implementation of the proposed HTM architecture.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Freeman, W.J.: How brains make up their minds. Columbia University Press, New York (2000)
George, D., Jaros, B.: The HTM learning algorithms. Tech. rep., Numenta, Inc., Palto Alto (2007), www.numenta.com/htm-overview/education/Numenta_HTM_Learning_Algos.pdf
Hawkins, J., Ahmad, S., Dubinsky, D.: Hierarchical temporal memory including HTM cortical learning algorithms. Tech. rep., Numenta, Inc., Palto Alto (2010), www.numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
Hawkins, J., Blakeslee, S.: On intelligence. Henry Holt, New York (2004)
Hawkins, J., George, D.: Hierarchical temporal memory: Concepts, theory and terminology. Tech. rep., Numenta, Inc., Palto Alto (2006), www.numenta.com/htm-overview/education/Numenta_HTM_Concepts.pdf
Hyvärinen, A., Hurri, J., Hoyer, P.: Natural Image Statistics: A probabilistic approach to early computational vision. Springer-Verlag New York Inc. (2009)
Kläser, A., Marszalek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: British Machine Vision Conference, BMVC 2008, pp. 995–1004 (2008)
Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (2008)
Le, Q., Zou, W., Yeung, S., Ng, A.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011), pp. 3361–3368 (2011)
Mountcastle, V.B.: Introduction to the special issue on computation in cortical columns. Cerebral Cortex 13(1), 2–4 (2003)
Price, R.W.: Hierarchical Temporal Memory Cortical Learning Algorithm for Pattern Recognition on Multi-core Architectures. Master’s thesis, Portland State University (2011)
Rozado, D., Rodriguez, F.B., Varona, P.: Extending the bioinspired hierarchical temporal memory paradigm for sign language recognition. Neurocomputing 79, 75–86 (2012)
Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: A local SVM approach. In: Proceedings of International Conference on Pattern Recognition (ICPR 2004), p. 3361, 3362, 3366 (2004)
Stuart, G., Spruston, N., Häusser, M.: Dendrites. Oxford University Press, New York (2008)
Thornton, J., Srbic, A.: Spatial pooling for greyscale images. International Journal of Machine Learning and Cybernetics 2, 1–10 (2012)
Wang, H., Yuan, C., Hu, W., Sun, C.: Supervised class-specific dictionary learning for sparse modeling in action recognition. Pattern Recognition 45, 3902–3911 (2012)
Wang, H., Ulla, M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: British Machine Vision Conference, BMVC 2009, pp. 127–138 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Thornton, J., Main, L., Srbic, A. (2012). Fixed Frame Temporal Pooling. In: Thielscher, M., Zhang, D. (eds) AI 2012: Advances in Artificial Intelligence. AI 2012. Lecture Notes in Computer Science(), vol 7691. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35101-3_60
Download citation
DOI: https://doi.org/10.1007/978-3-642-35101-3_60
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35100-6
Online ISBN: 978-3-642-35101-3
eBook Packages: Computer ScienceComputer Science (R0)