On multi-view feature learning

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 1, Issue , 2012, Pages 161-168

  Memisevic, Roland ^a  

^a GOETHE UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

CELL MODEL; EIGENSPACES; FEATURE LEARNING; HIDDEN VARIABLE; LOCAL FEATURE; MULTI-VIEWS; MULTIPLE IMAGE; ROTATION ANGLES; SINGLE IMAGES; SPARSE CODING; SPATIO-TEMPORAL;

ENCODING (SYMBOLS); OBJECT RECOGNITION;

LEARNING SYSTEMS;

EID: 84867123303     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Adelson, E.H. and Bergen, J.R. Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A, 2(2):284-299, 1985.
2. Bergstra, James, Bengio, Yoshua, and Louradour, Jérôme. Suitability of V1 energy models for object classification. Neural Computation, pp. 1-17, 2010.
3. Bethge, M, Gerwinn, S, and Macke, JH. Unsupervised learning of a steerable basis for invariant image representations. In Human Vision and Electronic Imaging XII. SPIE, February 2007.
4. Fleet, D., Wagner, H., and Heeger, D. Neural encoding of binocular disparity: Energy models, position shifts and phase shifts. Vision Research, 36(12):1839-1857, 1996.
5. Gray, Robert M. Toeplitz and circulant matrices: a review. Commun. Inf. Theory, 2:155-239, August 2005.
6. Horn, Roger A. and Johnson, Charles R. Matrix Analysis. Cambridge University Press, 1990.
7. Hyvärinen, Aapo and Hoyer, Patrik. Emergence of phase-and shift-invariant features by decomposition of natural images into independent feature subspaces. Neural Computation, 12:1705-1720, July 2000.
8. Hyvärinen, Aapo, Hurri, J., and Hoyer, Patrik O. Natural Image Statistics: A Probabilistic Approach to Early Computational Vision. Springer Verlag, 2009.
9. Kohonen, Teuvo. The Adaptive-Subspace SOM (ASSOM) and its use for the implementation of invariant feature detection. In Proc. ICANN'95, Int. Conf. on Artificial Neural Networks.
10. Larochelle, Hugo, Erhan, Dumitru, Courville, Aaron, Bergstra, James, and Bengio, Yoshua. An empirical evaluation of deep architectures on problems with many factors of variation. In Proceedings of the 24th international conference on Machine learning, 2007.
11. Le, Q.V., Zou, W.Y., Yeung, S.Y., and Ng, A.Y. Learning hierarchical spatio-temporal features for action recognition with independent subspace analysis. In Proc. CVPR, 2011. IEEE, 2011.
12. Memisevic, Roland. Gradient-based learning of higher-order image features. In Proceedings of the International Conference on Computer Vision, 2011.
13. Memisevic, Roland and Hinton, Geoffrey E. Learning to represent spatial transformations with factored higher-order Boltzmann machines. Neural Computation, 22(6): 1473-92, 2010.
14. Qian, Ning. Computing stereo disparity and motion with known binocular cell properties. Neural Computation, 6: 390-404, May 1994.
15. Ranzato, Marc'Aurelio and Hinton, Geoffrey E. Modeling Pixel Means and Covariances Using Factorized Third-Order Boltzmann Machines. In Computer Vision and Pattern Recognition, 2010.
16. Susskind, J., Memisevic, R., Hinton, G., and Pollefeys, M. Modeling the joint density of two images under a variety of transformations. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2011.
17. Taylor, Graham, W., Fergus, Rob, LeCun, Yann, and Bregler, Christoph. Convolutional learning of spatiotemporal features. In Proc. European Conference on Computer Vision, 2010.
18. van Hateren, L. and Ruderman, J. Independent component analysis of natural image sequences yields spatiotemporal filters similar to simple cells in primary visual cortex. Proc. Biological Sciences, 265(1412):2315-2320, 1998.