nips nips2001 nips2001-191 nips2001-191-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Chris Stauffer, Erik Miller, Kinh Tieu
Abstract: Recent work has shown impressive transform-invariant modeling and clustering for sets of images of objects with similar appearance. We seek to expand these capabilities to sets of images of an object class that show considerable variation across individual instances (e.g. pedestrian images) using a representation based on pixel-wise similarities, similarity templates. Because of its invariance to the colors of particular components of an object, this representation enables detection of instances of an object class and enables alignment of those instances. Further, this model implicitly represents the regions of color regularity in the class-specific image set enabling a decomposition of that object class into component regions. 1
[1] Jojic, N. and B. J. Frey. “Topographic transformation as a discrete latent variable.” In NIPS 12, S. A. Solla, T. K. Leen and K.-R. Muller (eds), MIT Press, Cambridge, MA.
[2] Miller, E., N. Matsakis, and P. Viola, (2000) ”Learning from One Example Through Shared Densities on Transforms.” CVPR2000, Vol. 1, pp. 464-471.
[3] Shi, J. and J. Malik. “Normalized Cuts and Image Segmentation,” In CVPR San juan, Puerto Rico, June 1997.
[4] Boykov, Y., O. Veksler and R. Zabih. Fast Approximate Energy Minimization via Graph Cuts, In ICCV (99), September 1999.
[5] Viola, P. Alignment by Maximization of Mutual Information. MIT Artificial Intelligence Lab, Ph.D. Thesis AI-TR #1548, June, 1995.
[6] Stauffer, C. and W.E.L. Grimson. “Similarity templates for detection and recognition,” submitted to CVPR (2001).
[7] Pereira, F.C., N. Tishby, and L. Lee. “Distributional clustering of English words.” In 30th Annual Meeting of the Association for Computational Linguistics, Columbus, Ohio, pages 183–190, 1993.
[8] Thomas Hofmann, “Probabilistic Latent Semantic Analysis,” UAI (99), Morgan Kaufmann Publishers, Inc., San Francisco, 1999.
[9] Lee, D. D. and H. S. Seung. “Learning the parts of objects by non-negative matrix factorization.” Nature 401, 788-791 (1999).
[10] Stauffer, C.. ”Automatic hierarchical classification using time-based co-occurrences.” CVPR (1999), Fort Colins, CO, (June 1999).