Multicamera Action Recognition with Canonical Correlation Analysis and Discriminative Sequence Classification - Foundations on Natural and Artificial Computation - page 498

made in that subspace. Although the results achieved have been inferior to the
obtained by state of the art 3D methods, we belief a non linear extension of the
method using a mixture of Canonical Correlation Analyzers would reduce the
gap [7].
Other strategy to test in the future would be to integrate the PCCA model
into a sequence manifold learning method such the introduced in [11], in order to
use the temporal evolution of the features for subspace regularization. Finally,
other strategy to try would be to integrate the action classification with the
resulting model, to perform the learning of the dimensionality reduction and the
action classes at the same time.
References
1. Bach, F., Jordan, M.: Kernel independent component analysis. The Journal of
Machine Learning Research 3, 1-48 (2003)
2. Bach, F., Jordan, M.: A probabilistic interpretation of canonical correlation anal-
ysis. Dept. Statist., Univ. California, Berkeley, CA, Tech. Rep 688 (2005)
3. Bobick, A., Davis, J.: The recognition of human movement using temporal tem-
plates. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(3),
257-267 (2001)
4. Cilla, R., Patricio, M.A., Berlanga, A., Molina, J.M.: Fusion of single view soft k-
NN classifiers for multicamera human action recognition. In: Corchado, E., Grana
Romay, M., Manhaes Savio, A. (eds.) HAIS 2010. LNCS, vol. 6077, pp. 436-443.
Springer, Heidelberg (2010)
5. Dasarathy, B.: Sensor fusion potential exploitation-innovative architectures and
illustrative applications. Proceedings of the IEEE 85(1), 24-38 (2002)
6. Hardoon, D., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an
overview with application to learning methods. Neural Computation 16(12),
2639-2664 (2004)
7. Klami, A., Kaski, S.: Local dependent components. In: Proceedings of the 24th
international conference on Machine learning, pp. 425-432. ACM, New York (2007)
8. Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic
models for segmenting and labeling sequence data. In: International Conference on
Machine Learning (2001)
9. Laurentini, A.: The visual hull concept for silhouette-based image understanding.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 150-162 (1994)
10. Lavee, G., Rivlin, E., Rudzsky, M.: Understanding Video Events: A Survey of
Methods for Automatic Interpretation of Semantic Occurrences in Video. IEEE
Transactions on Systems, Man and Cybernetics - Part C: Applications and Re-
views 39(5), 489-504 (2009)
11. Li, R., Tian, T., Sclaroff, S.: Simultaneous learning of nonlinear manifold and
dynamical models for high-dimensional time series. In: IEEE 11th International
Conference on Computer Vision, ICCV 2007, pp. 1-8. IEEE, Los Alamitos (2007)
12. Maatta, T., Harma, A., Aghajan, H.: On ecient use of multi-view data for activity
recognition. In: 4th IEEE/ACM International Conference on Distributed Smart
Cameras, ICSDC 2010, pp. 158-165 (2010)
13. Peng, B., Qian, G., Rajko, S.: View-Invariant Full-Body Gesture Recognition via
Multilinear Analysis of Voxel Data. In: Third ACM/IEEE Conference on Dis-
tributed Smart Cameras (September 2009)