nips nips2008 nips2008-201 nips2008-201-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Alex J. Smola, Julian J. Mcauley, Tibério S. Caetano
Abstract: Models for near-rigid shape matching are typically based on distance-related features, in order to infer matches that are consistent with the isometric assumption. However, real shapes from image datasets, even when expected to be related by “almost isometric” transformations, are actually subject not only to noise but also, to some limited degree, to variations in appearance and scale. In this paper, we introduce a graphical model that parameterises appearance, distance, and angle features and we learn all of the involved parameters via structured prediction. The outcome is a model for near-rigid shape matching which is robust in the sense that it is able to capture the possibly limited but still important scale and appearance variations. Our experimental results reveal substantial improvements upon recent successful models, while maintaining similar running times. 1
[1] Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24 (2002) 509–522
[2] Mori, G., Belongie, S., Malik, J.: Shape contexts enable efficient retrieval of similar shapes. In: CVPR. (2001) 723–730
[3] Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: ECCV. (2002) 666–680
[4] Frome, A., Huber, D., Kolluri, R., Bulow, T., Malik, J.: Recognizing objects in range data using regional point descriptors. In: ECCV. (2004)
[5] Belongie, S., Malik, J.: Matching with shape contexts. In: CBAIVL00. (2000) 20–26
[6] Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV. (1999) 1150–1157
[7] Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV 61 (2005) 55–79
[8] Felzenszwalb, P.F., Schwartz, J.D.: Hierarchical matching of deformable shapes. In: CVPR. (2007)
[9] LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. CVPR (2004) 97–104
[10] Carmichael, O., Hebert, M.: Shape-based recognition of wiry objects. PAMI 26 (2004) 1537–1552
[11] McAuley, J.J., Caetano, T.S., Barbosa, M.S.: Graph rigidity, cyclic belief propagation and point pattern matching. PAMI 30 (2008) 2047–2054
[12] Caetano, T., Cheng, L., Le, Q., Smola, A.: Learning graph matching. In: ICCV. (2007) 1–8
[13] Canny, J.: A computational approach to edge detection. In: RCV. (1987) 184–203
[14] Smith, S.: A new class of corner finder. In: BMVC. (1992) 139–148
[15] Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML. (2004)
[16] Teo, C., Le, Q., Smola, A., Vishwanathan, S.: A scalable modular convex solver for regularized risk minimization. In: KDD. (2007)
[17] Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. 60 (2004) 63–86
[18] Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology (2007) 8