nips nips2012 nips2012-360 nips2012-360-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Angela Eigenstetter, Bjorn Ommer
Abstract: Category-level object detection has a crucial need for informative object representations. This demand has led to feature descriptors of ever increasing dimensionality like co-occurrence statistics and self-similarity. In this paper we propose a new object representation based on curvature self-similarity that goes beyond the currently popular approximation of objects using straight lines. However, like all descriptors using second order statistics, ours also exhibits a high dimensionality. Although improving discriminability, the high dimensionality becomes a critical issue due to lack of generalization ability and curse of dimensionality. Given only a limited amount of training data, even sophisticated learning algorithms such as the popular kernel methods are not able to suppress noisy or superfluous dimensions of such high-dimensional data. Consequently, there is a natural need for feature selection when using present-day informative features and, particularly, curvature self-similarity. We therefore suggest an embedded feature selection method for SVMs that reduces complexity and improves generalization capability of object models. By successfully integrating the proposed curvature self-similarity representation together with the embedded feature selection in a widely used state-of-the-art object detection framework we show the general pertinence of the approach. 1
[1] S. Belongie, J. Malik, and J. Puzicha. Matching shapes. ICCV, 2001. 1 This work was supported by the Excellence Initiative of the German Federal Government and the Frontier fund, DFG project number ZUK 49/1. 8
[2] P. S. Bradley and O. L. Magasarian. Feature selection via concave minimization and support vector machines. ICML, 1998.
[3] C.-C Chang and C.-J. Lin. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27, 2011.
[4] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. CVPR, 2005.
[5] T. Deselaers and V. Ferrari. Global and efficient self-similarity for object classification and detection. CVPR, 2010.
[6] T.-M.-T. Do and T. Arti´ res. Large margin training for hidden markov models with partially observed e states. ICML, 2009.
[7] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http://www.pascalnetwork.org/challenges/VOC/voc2007/workshop/index.html.
[8] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. PAMI, 2010.
[9] P. F. Felzenszwalb, R. B. Girshick, and D. McAllester. Discriminatively trained deformable part models, release 4. http://www.cs.brown.edu/ pff/latent-release4/.
[10] W. T. Freeman and M. Roth. Orientation histograms for hand gesture recognition. Intl. Workshop on Automatic Face and Gesture- Recognition, 1995.
[11] Y. Grandvalet and S. Canu. Adaptive scaling for feature selection in SVMs. NIPS, 2003.
[12] I. Guyon and A. Elisseeff. An introduction to variable and feature selection. JMLR, 3:11571182, 2003.
[13] J. H. Han and T. Poston. Chord-to-point distance acccumulation and planar curvature: a new approach to discrete curvature. Pattern Recognition Letters, 22(10):1133 – 1144, 2001.
[14] G. Heitz and D. Koller. Learning spatial context: Using stuff to find things. ECCV, 2008.
[15] I. N. Junejo, E. Dexter, I. Laptec, and P. Per´ z. Cross-view action recognition from temporal selfe similarities. ECCV, 2008.
[16] N. Karmitsa, M. Tanaka Filho, and J. Herskovits. Globally convergent cutting plane method for nonconvex nonsmooth minimization. Journal of Optimization Theory and Applications, 148(3):528 – 549, 2011.
[17] T. N. Lal, O. Chapelle, J. Weston, and A. Elisseeff. Studies in Fuzziness and Soft Computing. I. Guyon and S. Gunn and N. Nikravesh and L. A. Zadeh, 2006.
[18] D.G. Lowe. Object recognition from local scale-invariant features. ICCV, 1999.
[19] S. Maji, A. C. Berg, and J. Malik. Classification using intersection kernel support vector machines is efficient. CVPR, 2008.
[20] D. Martin, C. Fowlkes, and J. Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues. PAMI, 26(5):530 – 549, 2004.
[21] A. Monroy, A. Eigenstetter, and B. Ommer. Beyond straight lines - object detection using curvature. ICIP, 2011.
[22] A. Monroy and B. Ommer. Beyond bounding-boxes: Learning object shape by model-driven grouping. ECCV, 2012.
[23] C. P. Papageorgiou, M. Oren, and T. Poggio. A general framwork for object detection. ICCV, 1998.
[24] P. Schnitzspan, M. Fritz, S. Roth, and B. Schiele. Discriminative structure learning of hierarchical representations for object detection. CVPR, 2009.
[25] E. Shechtman and M. Irani. Matching local self-similarities across images and videos. CVPR, 2007.
[26] Z. Song, Q. Chen, Z. Huang, Y. Hua, and S. Yan. Contextualizing object detection and classification. CVPR, 2011.
[27] I. Tsochantaridis, T. Hofmann, T. Joachims, and Y. Altun. Support vector learning for interdependent and structured output spaces. ICML, 2004.
[28] V. N. Vapnik. The Nature of Statistical Learning Theory. Springer Verlag, 1995.
[29] S. Walk, N. Majer, K. Schindler, and B. Schiele. New features and insights for pedestiran detection. CVPR, 2010.
[30] L. Wang, J. Zhu, and H. Zou. The doubly regularized support vector machine. Statistica Sinica, 16, 2006.
[31] L. Wolf, T. Hassner, and Y. Taigman. Descriptor based methods in the wild. ECCV, 2008.
[32] P. Yarlagadda and B. Ommer. From meaningful contours to discriminative object shape. ECCV, 2012.
[33] L. Zhu, Y. Chen, A. Yuille, and W. Freeman. Latent hierarchical structural learning for object detection. CVPR, pages 1062 –1069, 2010. 9