Abstract
The range space of dynamic textures spans spatiotemporal phenomena that vary along three fundamental dimensions: spatial texture, spatial texture layout, and dynamics. By describing each dimension with appropriate spatial or temporal features and by equipping it with a suitable distance measure, elementary distances (one for each dimension) between dynamic texture sequences can be computed. In this paper, we address the problem of dynamic texture (DT) recognition by learning linear combinations of these elementary distances. By learning weights to these distances, we shed light on how “salient” (in a discriminative manner) each DT dimension is in representing classes of dynamic textures. To do this, we propose an efficient maximum margin distance learning (MMDL) method based on the Pegasos algorithm [1], for both class-independent and class-dependent weight learning. In contrast to popular MMDL methods, which enforce restrictive distance constraints and have a computational complexity that is cubic in the number of training samples, we show that our method, called DL-PEGASOS, can handle more general distance constraints with a computational complexity that can be made linear. When class dependent weights are learned, we show that, for certain classes of DTs , spatial texture features are dominantly “salient”, while for other classes, this “saliency” lies in their temporal features. Furthermore, DL-PEGASOS outperforms state-of-the-art recognition methods on the UCLA benchmark DT dataset. By learning class independent weights, we show that this benchmark does not offer much variety along the three DT dimensions, thus, motivating the proposal of a new DT dataset, called DynTex++.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
Shalev-Shwartz, S., Singer, Y., Srebro, N.: Pegasos: Primal estimated sub-gradient solver for svm. In: ICML (2007)
Ghanem, B., Ahuja, N.: Extracting a fluid dynamic texture and the background from video. In: CVPR (2008)
Soatto, S., Doretto, G., Wu, Y.N.: Dynamic textures. IJCV 51, 91–109 (2003)
Chetverikov, D., Peteri, R.: A brief survey of dynamic texture description and recognition. In: International Conference on Computer Recognition Systems (2005)
Saisan, P., Doretto, G., Wu, Y.N., Soatto, S.: Dynamic texture recognition. In: CVPR, pp. 58–63 (2001)
Martin, R.J.: A metric for arma processes. IEEE Trans. on Signal Processing 48, 1164–1170 (2000)
Chan, A.B., Vasconcelos, N.: Probabilistic kernels for the classification of auto-regressive visual processes. CVPR 1, 846–851 (2005)
Woolfe, F., Fitzgibbon, A.W.: Shift-invariant dynamic texture recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 549–562. Springer, Heidelberg (2006)
Ravichandran, A., Chaudhry, R., Vidal, R.: View-invariant dynamic texture recognition using a bag of dynamical systems. In: CVPR, pp. 1651–1657 (2009)
Peteri, R., Chetverikov, D.: Dynamic texture recognition using normal flow and texture regularity. In: Iberian Conference on Pattern Recognition and Image Analysis (2005)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray scale and rotation invariant texture analysis with local binary patterns. TPAMI 24, 971–987 (2002)
Zhao, G., Pietikainen, M.: Local binary pattern descriptors for dynamic texture recognition. In: ICPR, vol. 2, pp. 211–214 (2006)
Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. TPAMI 29, 915–928 (2007)
Frome, A., Singer, Y., Sha, F., Malik, J.: Image retrieval and classification using local distance functions. In: NIPS (2006)
Frome, A., Singer, Y., Sha, F., Malik, J.: Learning globally-consistent local distance functions for shape-based image retrieval and classification. In: ICCV (2007)
Gu, C., Lim, J.J., Arbelaez, P., Malik, J.: Recognition using regions. In: CVPR, pp. 1030–1037. IEEE, Los Alamitos (2009)
Varma, M., Ray, D.: Learning the discriminative power-invariance trade-off. In: ICCV (2007)
Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: ICCV (2009)
Rubner, Y., Tomasi, C., Guibas, L.J.: A metric for distributions with applications to image databases. In: ICCV (1998)
Zhao, G., Pietikainen, M.: Dynamic texture recognition using volume local binary patterns. In: ECCV, Workshop on Dynamical Vision, pp. 12–23 (2006)
Wang, X., Han, T.X., Yan, S.: An hog-lbp human detector with partial occlusion handling. In: ICCV (2009)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)
Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR (2007)
Chan, A.B., Vasconcelos, N.: Classifying video with kernel dynamic textures. In: CVPR, vol. 1 (2007)
Peteri, R., Huiskes, M., Fazekas, S.: DynTex: the Centre for Mathematics and Computer Science (CWI), Amsterdam (2006), http://www.cwi.nl/projects/dyntex/
Gautama, T., Hulle, M.A.V.: A phase-based approach to the estimation of the optical flow field using spatial filtering. TNN 13, 1127–1136 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
1 Electronic Supplementary Material
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ghanem, B., Ahuja, N. (2010). Maximum Margin Distance Learning for Dynamic Texture Recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6312. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15552-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-15552-9_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15551-2
Online ISBN: 978-3-642-15552-9
eBook Packages: Computer ScienceComputer Science (R0)