nips nips2004 nips2004-53 nips2004-53-reference knowledge-graph by maker-knowledge-mining

53 nips-2004-Discriminant Saliency for Visual Recognition from Cluttered Scenes


Source: pdf

Author: Dashan Gao, Nuno Vasconcelos

Abstract: Saliency mechanisms play an important role when visual recognition must be performed in cluttered scenes. We propose a computational definition of saliency that deviates from existing models by equating saliency to discrimination. In particular, the salient attributes of a given visual class are defined as the features that enable best discrimination between that class and all other classes of recognition interest. It is shown that this definition leads to saliency algorithms of low complexity, that are scalable to large recognition problems, and is compatible with existing models of early biological vision. Experimental results demonstrating success in the context of challenging recognition problems are also presented. 1


reference text

[1] P. Viola and M. Jones. Robust real-time object detection. 2nd Int. Workshop on Statistical and Computational Theories of Vision Modeling, Learning, Computing and Sampling, July 2001.

[2] C. Harris and M. Stephens. A combined corner and edge detector. Alvey Vision Conference, 1988.

[3] A. Sha’ashua and S. Ullman. Structural saliency: the detection of globally salient structures using a locally connected network. Proc. Internat. Conf. on Computer Vision, 1988.

[4] D. G. Lowe. Object recognition from local scale-invariant features. In Proceedings of International Conference on Computer Vision, pp. 1150-1157, 1999.

[5] N. Sebe, M. S. Lew. Comparing salient point detectors. Pattern Recognition Letters, vol.24, no.1-3, Jan. 2003, pp.89-96.

[6] T. Kadir and M.l Brady. Scale, Saliency and Image Description. International Journal of Computer Vision, Vol.45, No.2, p83-105, November 2001

[7] L. Itti, C. Koch and E. Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Analysis and Machine Intelligence, 20(11), Nov. 1998.

[8] C. Schmid, R. Mohr and C. Bauckhage. Comparing and Evaluating Interest Points. Proceedings of International Conference on Computer Vision 1998, p.230-235.

[9] D. Claus and A. Fitzgibbon. Reliable Fiducial Detection in Natural Scenes. Proceedings of the 8th European Conference on Computer Vision, Prague, Czech Republic, 2004

[10] N. Vasconcelos. Feature Selection by Maximum Marginal Diversity. In Neural Information Processing System, Vancouver, Canada, 2002

[11] N. Vasconcelos. Scalable Discriminant Feature Selection for Image Retrieval and Recgnition. To appear in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2004

[12] D. Sagi, ”The Psychophysics of Texture Segmentation, in Early Vision and Beyond, T. Papathomas, Ed., chapter 7. MIT Press, 1996.

[13] J. Malik, P. Perona. Preattentive texture discrimination with early vision mechanisms. J Opt Soc Am A. 7(5), 1990 May, p923-32.

[14] N. Vasconcelos and G. Carneiro. What is the Role of Independence for Visual Regognition? In Proc. European Conference on Computer Vision, Copenhagen, Denmark, 2002.

[15] R. Fergus, P. Perona and A. Zisserman. Object Class Recognition by Unsupervised ScaleInvariant Learning. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition 2003.